Search Results for author: Jiang Bian

Found 224 papers, 88 papers with code

An Analysis of WordNet’s Coverage of Gender Identity Using Twitter and The National Transgender Discrimination Survey

no code implementations GWC 2016 Amanda Hicks, Michael Rutherford, Christiane Fellbaum, Jiang Bian

While gender identities in the Western world are typically regarded as binary, our previous work (Hicks et al., 2015) shows that there is more lexical variety of gender identity and the way people identify their gender.

MIRA: Medical Time Series Foundation Model for Real-World Health Data

no code implementations9 Jun 2025 Hao Li, Bowen Deng, Chang Xu, Zhiyuan Feng, Viktor Schlegel, Yu-Hao Huang, Yizheng Sun, Jingyuan Sun, Kailai Yang, Yiyao Yu, Jiang Bian

To address these challenges, we introduce MIRA, a unified foundation model specifically designed for medical time series forecasting.

Ethics Missing Values +3

Learning to Select In-Context Demonstration Preferred by Large Language Model

no code implementations26 May 2025 Zheng Zhang, Shaocheng Lan, Lei Song, Jiang Bian, Yexin Li, Kan Ren

In-context learning (ICL) enables large language models (LLMs) to adapt to new tasks during inference using only a few demonstrations.

In-Context Learning Language Modeling +4

Are Time-Series Foundation Models Deployment-Ready? A Systematic Study of Adversarial Robustness Across Domains

no code implementations26 May 2025 Jiawen Zhang, Zhenwei Zhang, Shun Zheng, Xumeng Wen, Jia Li, Jiang Bian

Time Series Foundation Models (TSFMs), which are pretrained on large-scale, cross-domain data and capable of zero-shot forecasting in new scenarios without further training, are increasingly adopted in real-world applications.

Adversarial Robustness Data Poisoning +1

R&D-Agent-Quant: A Multi-Agent Framework for Data-Centric Factors and Model Joint Optimization

2 code implementations21 May 2025 Yuante Li, Xu Yang, Xiao Yang, Minrui Xu, Xisen Wang, Weiqing Liu, Jiang Bian

Financial markets pose fundamental challenges for asset return prediction due to their high dimensionality, non-stationarity, and persistent volatility.

Code Generation Model Optimization

R&D-Agent: Automating Data-Driven AI Solution Building Through LLM-Powered Automated Research, Development, and Evolution

1 code implementation20 May 2025 Xu Yang, Xiao Yang, Shikai Fang, Bowen Xian, Yuante Li, Jian Wang, Minrui Xu, Haoran Pan, Xinpeng Hong, Weiqing Liu, Yelong Shen, Weizhu Chen, Jiang Bian

Recent advances in AI and ML have transformed data science, yet increasing complexity and expertise requirements continue to hinder progress.

Generating Full-field Evolution of Physical Dynamics from Irregular Sparse Observations

no code implementations14 May 2025 Panqi Chen, Yifan Sun, Lei Cheng, Yang Yang, Weichang Li, Yang Liu, Weiqing Liu, Jiang Bian, Shikai Fang

To fill the gaps, we present SDIFT, Sequential DIffusion in Functional Tucker space, a novel framework that generates full-field evolution of physical dynamics from irregular sparse observations.

Computational Efficiency Denoising

OMGM: Orchestrate Multiple Granularities and Modalities for Efficient Multimodal Retrieval

no code implementations10 May 2025 Wei Yang, Jingjing Fu, Rui Wang, Jinyu Wang, Lei Song, Jiang Bian

The effectiveness of Vision-language RAG systems hinges on multimodal retrieval, which is inherently challenging due to the diverse modalities and knowledge granularities in both queries and knowledge bases.

Cross-Modal Retrieval Question Answering +5

TarDiff: Target-Oriented Diffusion Guidance for Synthetic Electronic Health Record Time Series Generation

no code implementations24 Apr 2025 Bowen Deng, Chang Xu, Hao Li, Yuhao Huang, Min Hou, Jiang Bian

Synthetic Electronic Health Record (EHR) time-series generation is crucial for advancing clinical machine learning models, as it helps address data scarcity by providing more training data.

Synthetic Data Generation Time Series +1

MineWorld: a Real-Time and Open-Source Interactive World Model on Minecraft

no code implementations11 Apr 2025 Junliang Guo, Yang Ye, Tianyu He, HaoYu Wu, Yushu Jiang, Tim Pearce, Jiang Bian

In evaluation, we propose new metrics to assess not only visual quality but also the action following capacity when generating new scenes, which is crucial for a world model.

Minecraft

Evaluating LLM-based Agents for Multi-Turn Conversations: A Survey

no code implementations28 Mar 2025 Shengyue Guan, Haoyi Xiong, Jindong Wang, Jiang Bian, Bin Zhu, Jian-Guang Lou

This survey examines evaluation methods for large language model (LLM)-based agents in multi-turn conversational settings.

Large Language Model

Chemistry-aware battery degradation prediction under simulated real-world cyclic protocols

no code implementations25 Mar 2025 Yuqi Li, Han Zhang, Xiaofan Gui, Zhao Chen, Yu Li, Xiwen Chi, Quan Zhou, Shun Zheng, Ziheng Lu, Wei Xu, Jiang Bian, Liquan Chen, Hong Li

Battery degradation is governed by complex and randomized cyclic conditions, yet existing modeling and prediction frameworks usually rely on rigid, unchanging protocols that fail to capture real-world dynamics.

Prediction

Chain of Functions: A Programmatic Pipeline for Fine-Grained Chart Reasoning Data

no code implementations20 Mar 2025 Zijian Li, Jingjing Fu, Lei Song, Jiang Bian, Jun Zhang, Rui Wang

Employing \textit{CoF}, we construct the \textit{ChartCoF} dataset, with 1. 4k complex reasoning Q\&A for fine-grained analysis and 50k Q\&A for reasoning enhancement.

Diversity Visual Reasoning

Fast Autoregressive Video Generation with Diagonal Decoding

no code implementations18 Mar 2025 Yang Ye, Junliang Guo, HaoYu Wu, Tianyu He, Tim Pearce, Tabish Rashid, Katja Hofmann, Jiang Bian

Autoregressive Transformer models have demonstrated impressive performance in video generation, but their sequential token-by-token decoding process poses a major bottleneck, particularly for long videos represented by tens of thousands of tokens.

Video Generation

BRIDGE: Bootstrapping Text to Control Time-Series Generation via Multi-Agent Iterative Optimization and Diffusion Modelling

no code implementations4 Mar 2025 Hao Li, Yuhao Huang, Chang Xu, Viktor Schlegel, Renhe Jiang, Riza Batista-Navarro, Goran Nenadic, Jiang Bian

This approach achieves state-of-the-art generation fidelity on 11 of 12 datasets, and improves controllability by 12. 52% on MSE and 6. 34% MAE compared to no text input generation, highlighting its potential for generating tailored time-series data.

counterfactual Data Augmentation +2

AdaptiveStep: Automatically Dividing Reasoning Step through Model Confidence

1 code implementation19 Feb 2025 Yuliang Liu, Junjie Lu, Zhaoling Chen, Chaofeng Qu, Jason Klein Liu, Chonghan Liu, Zefan Cai, Yunhui Xia, Li Zhao, Jiang Bian, Chuheng Zhang, Wei Shen, Zhouhan Lin

Current approaches for training Process Reward Models (PRMs) often involve breaking down responses into multiple reasoning steps using rule-based techniques, such as using predefined placeholder tokens or setting the reasoning step's length into a fixed size.

Code Generation Decision Making +2

Functional Complexity-adaptive Temporal Tensor Decomposition

no code implementations10 Feb 2025 Panqi Chen, Lei Cheng, Jianlong Li, Weichang Li, Weiqing Liu, Jiang Bian, Shikai Fang

While recent works on temporal tensor decomposition have made significant progress by incorporating continuous timestamps in latent factors, they still struggle with general tensor data with continuous indexes not only in the temporal mode but also in other modes, such as spatial coordinates in climate data.

Tensor Decomposition Variational Inference

Scalable In-Context Learning on Tabular Data via Retrieval-Augmented Large Language Models

no code implementations5 Feb 2025 Xumeng Wen, Shun Zheng, Zhen Xu, Yiming Sun, Jiang Bian

Recent studies have shown that large language models (LLMs), when customized with post-training on tabular data, can acquire general tabular in-context learning (TabICL) capabilities.

In-Context Learning Retrieval

Text-to-CAD Generation Through Infusing Visual Feedback in Large Language Models

no code implementations31 Jan 2025 Ruiyu Wang, Yu Yuan, Shizhao Sun, Jiang Bian

In this work, we introduce CADFusion, a framework that uses Large Language Models (LLMs) as the backbone and alternates between two training stages: the sequential learning (SL) stage and the visual feedback (VF) stage.

PIKE-RAG: sPecIalized KnowledgE and Rationale Augmented Generation

1 code implementation20 Jan 2025 Jinyu Wang, Jingjing Fu, Rui Wang, Lei Song, Jiang Bian

Despite notable advancements in Retrieval-Augmented Generation (RAG) systems that expand large language model (LLM) capabilities through external retrieval, these systems often struggle to meet the complex and diverse needs of real-world industrial applications.

Language Modeling Language Modelling +4

TimeDP: Learning to Generate Multi-Domain Time Series with Domain Prompts

no code implementations9 Jan 2025 Yu-Hao Huang, Chang Xu, Yueying Wu, Wu-Jun Li, Jiang Bian

Time series generation models are crucial for applications like data augmentation and privacy preservation.

Data Augmentation Time Series +1

AR4D: Autoregressive 4D Generation from Monocular Videos

no code implementations3 Jan 2025 Hanxin Zhu, Tianyu He, Xiqian Yu, Junliang Guo, Zhibo Chen, Jiang Bian

To avoid appearance drift introduced by autoregressive generation, we further incorporate a refinement stage based on a global deformation field and the geometry of each frame's 3D representation.

3D Reconstruction Diversity +1

TimeRAF: Retrieval-Augmented Foundation model for Zero-shot Time Series Forecasting

no code implementations30 Dec 2024 Huanyu Zhang, Chang Xu, Yi-Fan Zhang, Zhang Zhang, Liang Wang, Jiang Bian, Tieniu Tan

In this paper, we introduce TimeRAF, a Retrieval-Augmented Forecasting model that enhance zero-shot time series forecasting through retrieval-augmented techniques.

RAG Retrieval +4

From Elements to Design: A Layered Approach for Automatic Graphic Design Composition

no code implementations CVPR 2025 Jiawei Lin, Shizhao Sun, Danqing Huang, Ting Liu, Ji Li, Jiang Bian

Based on the planning results, it subsequently predicts element attributes that control the design composition in a layer-wise manner, and includes the rendered image of previously generated layers into the context.

OMG-HD: A High-Resolution AI Weather Model for End-to-End Forecasts from Observations

no code implementations24 Dec 2024 Pengcheng Zhao, Jiang Bian, Zekun Ni, Weixin Jin, Jonathan Weyn, Zuliang Fang, Siqi Xiang, Haiyu Dong, Bin Zhang, Hongyu Sun, Kit Thambiratnam, Qi Zhang

In recent years, Artificial Intelligence Weather Prediction (AIWP) models have achieved performance comparable to, or even surpassing, traditional Numerical Weather Prediction (NWP) models by leveraging reanalysis data.

Computational Efficiency Weather Forecasting

VidTwin: Video VAE with Decoupled Structure and Dynamics

1 code implementation CVPR 2025 Yuchi Wang, Junliang Guo, Xinyi Xie, Tianyu He, Xu sun, Jiang Bian

Recent advancements in video autoencoders (Video AEs) have significantly improved the quality and efficiency of video generation.

Decoder Video Generation

AnalogXpert: Automating Analog Topology Synthesis by Incorporating Circuit Design Expertise into Large Language Models

no code implementations17 Dec 2024 Haoyi Zhang, Shizhao Sun, Yibo Lin, Runsheng Wang, Jiang Bian

Third, we introduce a proofreading strategy that allows LLMs to incrementally correct the errors in the initial design, akin to human designers who iteratively check and adjust the initial topology design to ensure accuracy.

2k Code Generation +1

VidTok: A Versatile and Open-Source Video Tokenizer

1 code implementation17 Dec 2024 Anni Tang, Tianyu He, Junliang Guo, Xinle Cheng, Li Song, Jiang Bian

Encoding video content into compact latent tokens has become a fundamental step in video generation and understanding, driven by the need to address the inherent redundancy in pixel-level representations.

Quantization SSIM +1

InvDiff: Invariant Guidance for Bias Mitigation in Diffusion Models

1 code implementation11 Dec 2024 Min Hou, Yueying Wu, Chang Xu, Yu-Hao Huang, Chenxi Bai, Le Wu, Jiang Bian

Then, we employ a lightweight trainable module that automatically preserves invariant semantic information and uses it to guide the diffusion model's sampling process toward unbiased outcomes simultaneously.

Image Generation

BPQP: A Differentiable Convex Optimization Framework for Efficient End-to-End Learning

no code implementations28 Nov 2024 Jianming Pan, Zeqi Ye, Xiao Yang, Xu Yang, Weiqing Liu, Lewen Wang, Jiang Bian

This reformulation enables the use of first-order optimization algorithms in calculating the backward pass gradients, allowing our framework to potentially utilize any state-of-the-art solver.

Identifying and Decomposing Compound Ingredients in Meal Plans Using Large Language Models

no code implementations8 Nov 2024 Leon Kopitar, Leon Bedrac, Larissa J Strath, Jiang Bian, Gregor Stiglic

This study explores the effectiveness of Large Language Models in meal planning, focusing on their ability to identify and decompose compound ingredients.

Nutrition

FlexCAD: Unified and Versatile Controllable CAD Generation with Fine-tuned Large Language Models

1 code implementation5 Nov 2024 Zhanwei Zhang, Shizhao Sun, Wenxiao Wang, Deng Cai, Jiang Bian

First, to enhance comprehension by LLMs, we represent a CAD model as a structured text by abstracting each hierarchy as a sequence of text tokens.

ElasTST: Towards Robust Varied-Horizon Forecasting with Elastic Time-Series Transformer

1 code implementation4 Nov 2024 Jiawen Zhang, Shun Zheng, Xumeng Wen, Xiaofang Zhou, Jiang Bian, Jia Li

Numerous industrial sectors necessitate models capable of providing robust forecasts across various horizons.

Position Time Series +1

Pre-trained Molecular Language Models with Random Functional Group Masking

no code implementations3 Nov 2024 Tianhao Peng, Yuchen Li, Xuhong LI, Jiang Bian, Zeke Xie, Ning Sui, Shahid Mumtaz, Yanwu Xu, Linghe Kong, Haoyi Xiong

Recent advancements in computational chemistry have leveraged the power of trans-former-based language models, such as MoLFormer, pre-trained using a vast amount of simplified molecular-input line-entry system (SMILES) sequences, to understand and predict molecular properties and activities, a critical step in fields like drug discovery and materials science.

Computational chemistry Drug Discovery

Diffusion Models in 3D Vision: A Survey

no code implementations7 Oct 2024 Zhen Wang, Dongyuan Li, Yaozu Wu, Tianyu He, Jiang Bian, Renhe Jiang

In recent years, 3D vision has become a crucial field within computer vision, powering a wide range of applications such as autonomous driving, robotics, augmented reality, and medical imaging.

Autonomous Driving Computational Efficiency +3

C-MORL: Multi-Objective Reinforcement Learning through Efficient Discovery of Pareto Front

1 code implementation3 Oct 2024 Ruohong Liu, Yuxin Pan, Linjie Xu, Lei Song, Jiang Bian, Pengcheng You, Yize Chen

Multi-objective reinforcement learning (MORL) excels at handling rapidly changing preferences in tasks that involve multiple criteria, even for unseen preferences.

continuous-control Continuous Control +1

FlashMask: Efficient and Rich Mask Extension of FlashAttention

1 code implementation2 Oct 2024 Guoxia Wang, Jinle Zeng, Xiyuan Xiao, Siming Wu, Jiabin Yang, Lujing Zheng, Zeyu Chen, Jiang Bian, dianhai yu, Haifeng Wang

In this paper, we propose FlashMask, an extension of FlashAttention that introduces a column-wise sparse representation of attention masks.

Computational Efficiency

Generative Pre-trained Ranking Model with Over-parameterization at Web-Scale (Extended Abstract)

no code implementations25 Sep 2024 Yuchen Li, Haoyi Xiong, Linghe Kong, Jiang Bian, Shuaiqiang Wang, Guihai Chen, Dawei Yin

Learning to rank (LTR) is widely employed in web searches to prioritize pertinent webpages from retrieved content based on input queries.

Learning-To-Rank

Beyond Skip Connection: Pooling and Unpooling Design for Elimination Singularities

no code implementations20 Sep 2024 Chengkun Sun, Jinqian Pan, Zhuoli Jin, Russell Stevens Terry, Jiang Bian, Jie Xu

Training deep Convolutional Neural Networks (CNNs) presents unique challenges, including the pervasive issue of elimination singularities, consistent deactivation of nodes leading to degenerate manifolds within the loss landscape.

GASA-UNet: Global Axial Self-Attention U-Net for 3D Medical Image Segmentation

no code implementations20 Sep 2024 Chengkun Sun, Russell Stevens Terry, Jiang Bian, Jie Xu

Accurate segmentation of multiple organs and the differentiation of pathological tissues in medical imaging are crucial but challenging, especially for nuanced classifications and ambiguous organ boundaries.

Image Segmentation Medical Image Segmentation +1

WeatherReal: A Benchmark Based on In-Situ Observations for Evaluating Weather Models

1 code implementation14 Sep 2024 Weixin Jin, Jonathan Weyn, Pengcheng Zhao, Siqi Xiang, Jiang Bian, Zuliang Fang, Haiyu Dong, Hongyu Sun, Kit Thambiratnam, Qi Zhang

Our work aims to advance the AI-based weather forecasting research towards a more application-focused and operation-ready approach.

Weather Forecasting

Enhancing Cross-domain Pre-Trained Decision Transformers with Adaptive Attention

no code implementations11 Sep 2024 Wenhao Zhao, Qiushui Xu, Linjie Xu, Lei Song, Jinyu Wang, Chunlai Zhou, Jiang Bian

Although this cross-domain pre-training approach achieves superior performance compared to training from scratch in environments required short-term planning ability, the mechanisms by which pre-training benefits the fine-tuning phase remain unclear.

Offline RL

MarS: a Financial Market Simulation Engine Powered by Generative Foundation Model

1 code implementation4 Sep 2024 Junjie Li, Yang Liu, Weiqing Liu, Shikai Fang, Lewen Wang, Chang Xu, Jiang Bian

Generative models aim to simulate realistic effects of various actions across different contexts, from text generation to visual effects.

Language Modeling Language Modelling +1

Compositional 3D-aware Video Generation with LLM Director

no code implementations31 Aug 2024 Hanxin Zhu, Tianyu He, Anni Tang, Junliang Guo, Zhibo Chen, Jiang Bian

Specifically, given an input textual prompt, our scheme consists of three stages: 1) We leverage LLM as the director to first decompose the complex query into several sub-prompts that indicate individual concepts within the video~(\textit{e. g.}, scene, objects, motions), then we let LLM to invoke pre-trained expert models to obtain corresponding 3D representations of concepts.

Text-to-Video Generation Video Generation

Collaborative Evolving Strategy for Automatic Data-Centric Development

1 code implementation26 Jul 2024 Xu Yang, Haotian Chen, Wenjun Feng, Haoxue Wang, Zeqi Ye, Xinjie Shen, Xiao Yang, Shizhao Sun, Weiqing Liu, Jiang Bian

By leveraging the strong complex problem-solving capabilities of large language models (LLMs), we propose an LLM-based autonomous agent, equipped with a strategy named Collaborative Knowledge-STudying-Enhanced Evolution by Retrieval (Co-STEER), to simultaneously address all the challenges.

Scheduling

UF-HOBI at "Discharge Me!": A Hybrid Solution for Discharge Summary Generation Through Prompt-based Tuning of GatorTronGPT Models

no code implementations22 Jul 2024 Mengxian Lyu, Cheng Peng, Daniel Paredes, Ziyi Chen, Aokun Chen, Jiang Bian, Yonghui Wu

This paper presents a hybrid solution for generating discharge summary sections as part of our participation in the "Discharge Me!"

NER

Towards Automated Data Sciences with Natural Language and SageCopilot: Practices and Lessons Learned

no code implementations21 Jul 2024 Yuan Liao, Jiang Bian, Yuhui Yun, Shuo Wang, Yubo Zhang, Jiaming Chu, Tao Wang, Kewei Li, Yuchen Li, Xuhong LI, Shilei Ji, Haoyi Xiong

While the field of NL2SQL has made significant advancements in translating natural language instructions into executable SQL scripts for data querying and processing, achieving full automation within the broader data science pipeline - encompassing data querying, analysis, visualization, and reporting - remains a complex challenge.

In-Context Learning

Hard Prompts Made Interpretable: Sparse Entropy Regularization for Prompt Tuning with RL

1 code implementation20 Jul 2024 Yunseon Choi, Sangmin Bae, Seonghyun Ban, Minchan Jeong, Chuheng Zhang, Lei Song, Li Zhao, Jiang Bian, Kee-Eung Kim

With the advent of foundation models, prompt tuning has positioned itself as an important technique for directing model behaviors and eliciting desired responses.

Few-Shot Text Classification Q-Learning +5

Converging Paradigms: The Synergy of Symbolic and Connectionist AI in LLM-Empowered Autonomous Agents

no code implementations11 Jul 2024 Haoyi Xiong, Zhiyuan Wang, Xuhong LI, Jiang Bian, Zeke Xie, Shahid Mumtaz, Anwer Al-Dulaimi, Laura E. Barnes

This article explores the convergence of connectionist and symbolic artificial intelligence (AI), from historical debates to contemporary advancements.

Decision Making Knowledge Graphs

Video In-context Learning

no code implementations10 Jul 2024 Wentao Zhang, Junliang Guo, Tianyu He, Li Zhao, Linli Xu, Jiang Bian

In-context learning for vision data has been underexplored compared with that in natural language.

In-Context Learning

Generative AI for Health Technology Assessment: Opportunities, Challenges, and Policy Considerations

no code implementations9 Jul 2024 Rachael Fleurence, Jiang Bian, Xiaoyan Wang, Hua Xu, Dalia Dawoud, Mitch Higashi, Jagpreet Chhatwal

This review introduces the transformative potential of generative Artificial Intelligence (AI) and foundation models, including large language models (LLMs), for health technology assessment (HTA).

When Search Engine Services meet Large Language Models: Visions and Challenges

no code implementations28 Jun 2024 Haoyi Xiong, Jiang Bian, Yuchen Li, Xuhong LI, Mengnan Du, Shuaiqiang Wang, Dawei Yin, Sumi Helal

Combining Large Language Models (LLMs) with search engine services marks a significant shift in the field of services computing, opening up new possibilities to enhance how we search for and retrieve information, understand content, and interact with internet services.

Learning-To-Rank

Make Your Actor Talk: Generalizable and High-Fidelity Lip Sync with Motion and Appearance Disentanglement

no code implementations12 Jun 2024 Runyi Yu, Tianyu He, Ailing Zhang, Yuchi Wang, Junliang Guo, Xu Tan, Chang Liu, Jie Chen, Jiang Bian

Instead, we propose to disentangle the motion and appearance, and then generate them one by one with a speech-to-motion diffusion model and a motion-conditioned appearance generation model.

Disentanglement Motion Generation

MAP: Low-compute Model Merging with Amortized Pareto Fronts via Quadratic Approximation

1 code implementation11 Jun 2024 Lu Li, Tianyu Zhang, Zhiqi Bu, Suyuchen Wang, Huan He, Jie Fu, Yonghui Wu, Jiang Bian, Yong Chen, Yoshua Bengio

MAP efficiently identifies a Pareto set of scaling coefficients for merging multiple models, reflecting the trade-offs involved.

Graph Neural Network Enhanced Retrieval for Question Answering of LLMs

no code implementations3 Jun 2024 Zijian Li, Qingyan Guo, Jiawei Shao, Lei Song, Jiang Bian, Jun Zhang, Rui Wang

A graph neural network (GNN) is then leveraged to exploit the relationships between passages and improve the retrieval of supporting passages.

Graph Neural Network Language Modelling +4

Position: Rethinking Post-Hoc Search-Based Neural Approaches for Solving Large-Scale Traveling Salesman Problems

1 code implementation2 Jun 2024 Yifan Xia, Xianliang Yang, Zichuan Liu, Zhihao Liu, Lei Song, Jiang Bian

Recent advancements in solving large-scale traveling salesman problems (TSP) utilize the heatmap-guided Monte Carlo tree search (MCTS) paradigm, where machine learning (ML) models generate heatmaps, indicating the probability distribution of each edge being part of the optimal solution, to guide MCTS in solution finding.

Position

InstructAvatar: Text-Guided Emotion and Motion Control for Avatar Generation

1 code implementation24 May 2024 Yuchi Wang, Junliang Guo, Jianhong Bai, Runyi Yu, Tianyu He, Xu Tan, Xu sun, Jiang Bian

Recent talking avatar generation models have made strides in achieving realistic and accurate lip synchronization with the audio, but often fall short in controlling and conveying detailed expressions and emotions of the avatar, making the generated video less vivid and controllable.

A Survey on Diffusion Models for Time Series and Spatio-Temporal Data

2 code implementations29 Apr 2024 Yiyuan Yang, Ming Jin, Haomin Wen, Chaoli Zhang, Yuxuan Liang, Lintao Ma, Yi Wang, Chenghao Liu, Bin Yang, Zenglin Xu, Jiang Bian, Shirui Pan, Qingsong Wen

Conditioned models, on the other hand, utilize extra information to enhance performance and are similarly divided for both predictive and generative tasks.

Anomaly Detection Imputation +1

DPO Meets PPO: Reinforced Token Optimization for RLHF

1 code implementation29 Apr 2024 Han Zhong, Zikang Shan, Guhao Feng, Wei Xiong, Xinle Cheng, Li Zhao, Di He, Jiang Bian, LiWei Wang

For its practical implementation, \texttt{RTO} innovatively integrates Direct Preference Optimization (DPO) and PPO.

Deep Reinforcement Learning reinforcement-learning +1

Protecting Your LLMs with Information Bottleneck

2 code implementations22 Apr 2024 Zichuan Liu, Zefan Wang, Linjie Xu, Jinyu Wang, Lei Song, Tianchun Wang, Chunlin Chen, Wei Cheng, Jiang Bian

The advent of large language models (LLMs) has revolutionized the field of natural language processing, yet they might be attacked to produce harmful content.

©Plug-in Authorization for Human Content Copyright Protection in Text-to-Image Model

1 code implementation18 Apr 2024 Chao Zhou, Huishuai Zhang, Jiang Bian, Weiming Zhang, Nenghai Yu

To mitigate this, we propose the \copyright Plug-in Authorization framework, introducing three operations: addition, extraction, and combination.

Towards Data-Centric Automatic R&D

1 code implementation17 Apr 2024 Haotian Chen, Xinjie Shen, Zeqi Ye, Wenjun Feng, Haoxue Wang, Xiao Yang, Xu Yang, Weiqing Liu, Jiang Bian

We appeal to future work to take developing techniques for tackling automatic R&D into consideration, thus bringing the opportunities of the potential revolutionary upgrade to human productivity.

Language Modelling Large Language Model +1

Empowering Large Language Models on Robotic Manipulation with Affordance Prompting

no code implementations17 Apr 2024 Guangran Cheng, Chuheng Zhang, Wenzhe Cai, Li Zhao, Changyin Sun, Jiang Bian

While large language models (LLMs) are successful in completing various language processing tasks, they easily fail to interact with the physical world by generating control sequences properly.

End-to-End Rate-Distortion Optimized 3D Gaussian Representation

1 code implementation9 Apr 2024 Henan Wang, Hanxin Zhu, Tianyu He, Runsen Feng, Jiajun Deng, Jiang Bian, Zhibo Chen

3D Gaussian Splatting (3DGS) has become an emerging technique with remarkable potential in 3D representation and image rendering.

3DGS Quantization

Improving Generalizability of Extracting Social Determinants of Health Using Large Language Models through Prompt-tuning

no code implementations19 Mar 2024 Cheng Peng, Zehao Yu, Kaleb E Smith, Wei-Hsuan Lo-Ciganic, Jiang Bian, Yonghui Wu

The progress in natural language processing (NLP) using large language models (LLMs) has greatly improved patient information extraction from clinical narratives.

Decoder Transfer Learning

Automatic Summarization of Doctor-Patient Encounter Dialogues Using Large Language Model through Prompt Tuning

no code implementations19 Mar 2024 Mengxian Lyu, Cheng Peng, Xiaohan Li, Patrick Balian, Jiang Bian, Yonghui Wu

We examined the prompt-tuning strategies, the size of soft prompts, and the few-short learning ability of GatorTronGPT, a generative clinical LLM developed using 277 billion clinical and general English words with up to 20 billion parameters.

Language Modeling Language Modelling +2

MG-TSD: Multi-Granularity Time Series Diffusion Models with Guided Learning Process

1 code implementation9 Mar 2024 Xinyao Fan, Yueying Wu, Chang Xu, Yuhao Huang, Weiqing Liu, Jiang Bian

However, the effective utilization of their strong modeling ability in the probabilistic time series forecasting task remains an open question, partially due to the challenge of instability arising from their stochastic nature.

Probabilistic Time Series Forecasting Time Series +1

NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models

1 code implementation5 Mar 2024 Zeqian Ju, Yuancheng Wang, Kai Shen, Xu Tan, Detai Xin, Dongchao Yang, Yanqing Liu, Yichong Leng, Kaitao Song, Siliang Tang, Zhizheng Wu, Tao Qin, Xiang-Yang Li, Wei Ye, Shikun Zhang, Jiang Bian, Lei He, Jinyu Li, Sheng Zhao

Specifically, 1) we design a neural codec with factorized vector quantization (FVQ) to disentangle speech waveform into subspaces of content, prosody, timbre, and acoustic details; 2) we propose a factorized diffusion model to generate attributes in each subspace following its corresponding prompt.

Quantization Speech Synthesis +2

Mitigating Reversal Curse in Large Language Models via Semantic-aware Permutation Training

1 code implementation1 Mar 2024 Qingyan Guo, Rui Wang, Junliang Guo, Xu Tan, Jiang Bian, Yujiu Yang

Accordingly, permutation on the training data is considered as a potential solution, since this can make the model predict antecedent words or tokens.

Language Modelling

Me LLaMA: Foundation Large Language Models for Medical Applications

1 code implementation20 Feb 2024 Qianqian Xie, Qingyu Chen, Aokun Chen, Cheng Peng, Yan Hu, Fongci Lin, Xueqing Peng, Jimin Huang, Jeffrey Zhang, Vipina Keloth, Xinyu Zhou, Lingfei Qian, Huan He, Dennis Shung, Lucila Ohno-Machado, Yonghui Wu, Hua Xu, Jiang Bian

This work underscores the importance of domain-specific data in developing medical LLMs and addresses the high computational costs involved in training, highlighting a balance between pre-training and fine-tuning strategies.

Few-Shot Learning

UniEdit: A Unified Tuning-Free Framework for Video Motion and Appearance Editing

no code implementations20 Feb 2024 Jianhong Bai, Tianyu He, Yuchi Wang, Junliang Guo, Haoji Hu, Zuozhu Liu, Jiang Bian

Recent advances in text-guided video editing have showcased promising results in appearance editing (e. g., stylization).

Video Editing

Addressing Distribution Shift in Time Series Forecasting with Instance Normalization Flows

no code implementations30 Jan 2024 Wei Fan, Shun Zheng, Pengyang Wang, Rui Xie, Jiang Bian, Yanjie Fu

Due to non-stationarity of time series, the distribution shift problem largely hinders the performance of time series forecasting.

Time Series Time Series Forecasting

MG-TSD: Multi-Granularity Time Series Diffusion Models with Guided Learning Process Download PDF

1 code implementation ICLR2024 2024 Xinyao Fan, Yueying Wu, Chang Xu, Yuhao Huang, Weiqing Liu, Jiang Bian

To address this challenge, we introduce a novel Multi-Granularity Time Series Diffusion (MG-TSD) model, which achieves state-of-the-art predictive performance by leveraging the inherent granularity levels within the data as given targets at intermediate diffusion steps to guide the learning process of diffusion models.

Probabilistic Time Series Forecasting Time Series +1

Morphological Profiling for Drug Discovery in the Era of Deep Learning

no code implementations13 Dec 2023 Qiaosi Tang, Ranjala Ratnayake, Gustavo Seabra, Zhe Jiang, Ruogu Fang, Lina Cui, Yousong Ding, Tamer Kahveci, Jiang Bian, Chenglong Li, Hendrik Luesch, Yanjun Li

Additionally, we illuminate the application of morphological profiling in phenotypic drug discovery and highlight potential challenges and opportunities in this field.

Cell Segmentation Deep Learning +3

Generative Large Language Models Are All-purpose Text Analytics Engines: Text-to-text Learning Is All Your Need

no code implementations11 Dec 2023 Cheng Peng, Xi Yang, Aokun Chen, Zehao Yu, Kaleb E Smith, Anthony B Costa, Mona G Flores, Jiang Bian, Yonghui Wu

Objective To solve major clinical natural language processing (NLP) tasks using a unified text-to-text learning architecture based on a generative large language model (LLM) via prompt tuning.

All Language Modelling +4

GAIA: Zero-shot Talking Avatar Generation

no code implementations26 Nov 2023 Tianyu He, Junliang Guo, Runyi Yu, Yuchi Wang, Jialiang Zhu, Kaikai An, Leyi Li, Xu Tan, Chunyu Wang, Han Hu, HsiangTao Wu, Sheng Zhao, Jiang Bian

Zero-shot talking avatar generation aims at synthesizing natural talking videos from speech and a single portrait image.

Diversity

On the Generalization Properties of Diffusion Models

1 code implementation NeurIPS 2023 Puheng Li, Zhong Li, Huishuai Zhang, Jiang Bian

This precisely elucidates the adverse effect of "modes shift" in ground truths on the model generalization.

BatteryML:An Open-source platform for Machine Learning on Battery Degradation

1 code implementation23 Oct 2023 Han Zhang, Xiaofan Gui, Shun Zheng, Ziheng Lu, Yuqi Li, Jiang Bian

Battery degradation remains a pivotal concern in the energy storage domain, with machine learning emerging as a potent tool to drive forward insights and solutions.

MusicAgent: An AI Agent for Music Understanding and Generation with Large Language Models

1 code implementation18 Oct 2023 Dingyao Yu, Kaitao Song, Peiling Lu, Tianyu He, Xu Tan, Wei Ye, Shikun Zhang, Jiang Bian

For developers and amateurs, it is very difficult to grasp all of these task to satisfy their requirements in music processing, especially considering the huge differences in the representations of music data and the model applicability across platforms among various tasks.

AI Agent Music Classification

Leveraging Large Language Model for Automatic Evolving of Industrial Data-Centric R&D Cycle

no code implementations17 Oct 2023 Xu Yang, Xiao Yang, Weiqing Liu, Jinhui Li, Peng Yu, Zeqi Ye, Jiang Bian

In the wake of relentless digital transformation, data-driven solutions are emerging as powerful tools to address multifarious industrial tasks such as forecasting, anomaly detection, planning, and even complex decision-making.

Anomaly Detection Decision Making +3

From Supervised to Generative: A Novel Paradigm for Tabular Deep Learning with Large Language Models

no code implementations11 Oct 2023 Xumeng Wen, Han Zhang, Shun Zheng, Wei Xu, Jiang Bian

Through GTL, we not only foster a deeper integration of LLMs' sophisticated abilities into tabular data comprehension and application but also offer a new training resource and a test bed for LLMs to enhance their ability to comprehend tabular data.

In-Context Learning Instruction Following +3

ProbTS: Benchmarking Point and Distributional Forecasting across Diverse Prediction Horizons

1 code implementation11 Oct 2023 Jiawen Zhang, Xumeng Wen, Zhenwei Zhang, Shun Zheng, Jia Li, Jiang Bian

Delivering precise point and distributional forecasts across a spectrum of prediction horizons represents a significant and enduring challenge in the application of time-series forecasting within various industries.

Benchmarking Position +2

NuTime: Numerically Multi-Scaled Embedding for Large-Scale Time-Series Pretraining

1 code implementation11 Oct 2023 Chenguo Lin, Xumeng Wen, Wei Cao, Congrui Huang, Jiang Bian, Stephen Lin, Zhirong Wu

In this work, we make key technical contributions that are tailored to the numerical properties of time-series data and allow the model to scale to large datasets, e. g., millions of temporal sequences.

Anomaly Detection Few-Shot Learning +3

Accurate battery lifetime prediction across diverse aging conditions with deep learning

no code implementations8 Oct 2023 Han Zhang, Yuqi Li, Shun Zheng, Ziheng Lu, Xiaofan Gui, Wei Xu, Jiang Bian

Here we introduce a universal deep learning approach that is capable of accommodating various aging conditions and facilitating effective learning under low-resource conditions by leveraging data from rich conditions.

Single-cell modeling

TiC: Exploring Vision Transformer in Convolution

1 code implementation6 Oct 2023 Song Zhang, Qingzhong Wang, Jiang Bian, Haoyi Xiong

While models derived from Vision Transformers (ViTs) have been phonemically surging, pre-trained models cannot seamlessly adapt to arbitrary resolution images without altering the architecture and configuration, such as sampling the positional encoding, limiting their flexibility for various vision tasks.

image-classification Image Classification

Natural Language based Context Modeling and Reasoning for Ubiquitous Computing with Large Language Models: A Tutorial

no code implementations24 Sep 2023 Haoyi Xiong, Jiang Bian, Sijia Yang, Xiaofei Zhang, Linghe Kong, Daqing Zhang

Recently, with the rise of LLMs and their improved natural language understanding and reasoning capabilities, it has become feasible to model contexts using natural language and perform context reasoning by interacting with LLMs such as ChatGPT and GPT-4.

Natural Language Understanding Scheduling

EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizers

2 code implementations15 Sep 2023 Qingyan Guo, Rui Wang, Junliang Guo, Bei Li, Kaitao Song, Xu Tan, Guoqing Liu, Jiang Bian, Yujiu Yang

Large Language Models (LLMs) excel in various tasks, but they rely on carefully crafted prompts that often demand substantial human effort.

Evolutionary Algorithms

PromptTTS 2: Describing and Generating Voices with Text Prompt

no code implementations5 Sep 2023 Yichong Leng, Zhifang Guo, Kai Shen, Xu Tan, Zeqian Ju, Yanqing Liu, Yufei Liu, Dongchao Yang, Leying Zhang, Kaitao Song, Lei He, Xiang-Yang Li, Sheng Zhao, Tao Qin, Jiang Bian

TTS approaches based on the text prompt face two main challenges: 1) the one-to-many problem, where not all details about voice variability can be described in the text prompt, and 2) the limited availability of text prompt datasets, where vendors and large cost of data labeling are required to write text prompts for speech.

Language Modelling Large Language Model +2

Developing A Fair Individualized Polysocial Risk Score (iPsRS) for Identifying Increased Social Risk of Hospitalizations in Patients with Type 2 Diabetes (T2D)

no code implementations5 Sep 2023 Yu Huang, Jingchuan Guo, William T Donahoo, Zhengkang Fan, Ying Lu, Wei-Han Chen, Huilin Tang, Lori Bilello, Elizabeth A Shenkman, Jiang Bian

Background: Racial and ethnic minority groups and individuals facing social disadvantages, which often stem from their social determinants of health (SDoH), bear a disproportionate burden of type 2 diabetes (T2D) and its complications.

Fairness

Hypergraph Convolutional Networks for Fine-grained ICU Patient Similarity Analysis and Risk Prediction

no code implementations24 Aug 2023 Yuxi Liu, Zhenhao Zhang, Shaowen Qin, Flora D. Salim, Antonio Jimeno Yepes, Jun Shen, Jiang Bian

In this paper, we propose a novel Hypergraph Convolutional Network that allows the representation of non-pairwise relationships among diagnosis codes in a hypergraph to capture the hidden feature structures so that fine-grained patient similarity can be calculated for personalized mortality risk prediction.

Decision Making Prediction

Microstructure-Empowered Stock Factor Extraction and Utilization

no code implementations16 Aug 2023 Xianfeng Jiao, Zizhong Li, Chang Xu, Yang Liu, Weiqing Liu, Jiang Bian

To address these challenges, we propose a novel framework that aims to effectively extract essential factors from order flow data for diverse downstream tasks across different granularities and scenarios.

Stock Trend Prediction

Pre-Trained Large Language Models for Industrial Control

no code implementations6 Aug 2023 Lei Song, Chuheng Zhang, Li Zhao, Jiang Bian

2)~How well can GPT-4 generalize to different scenarios for HVAC control?

Improving Primary Healthcare Workflow Using Extreme Summarization of Scientific Literature Based on Generative AI

no code implementations24 Jul 2023 Gregor Stiglic, Leon Kopitar, Lucija Gosak, Primoz Kocbek, Zhe He, Prithwish Chakraborty, Pablo Meyer, Jiang Bian

The time needed to answer questions related to the content of abstracts was significantly lower in groups two and three compared to the first group using full abstracts.

Extreme Summarization

Learning Multi-Agent Intention-Aware Communication for Optimal Multi-Order Execution in Finance

no code implementations6 Jul 2023 Yuchen Fang, Zhenggang Tang, Kan Ren, Weiqing Liu, Li Zhao, Jiang Bian, Dongsheng Li, Weinan Zhang, Yong Yu, Tie-Yan Liu

Order execution is a fundamental task in quantitative finance, aiming at finishing acquisition or liquidation for a number of trading orders of the specific assets.

Reinforcement Learning (RL)

EmoGen: Eliminating Subjective Bias in Emotional Music Generation

1 code implementation3 Jul 2023 Chenfei Kang, Peiling Lu, Botao Yu, Xu Tan, Wei Ye, Shikun Zhang, Jiang Bian

In this paper, we propose EmoGen, an emotional music generation system that leverages a set of emotion-related music attributes as the bridge between emotion and music, and divides the generation into two stages: emotion-to-attribute mapping with supervised clustering, and attribute-to-music generation with self-supervised learning.

Attribute Clustering +2

Warpformer: A Multi-scale Modeling Approach for Irregular Clinical Time Series

1 code implementation14 Jun 2023 Jiawen Zhang, Shun Zheng, Wei Cao, Jiang Bian, Jia Li

Irregularly sampled multivariate time series are ubiquitous in various fields, particularly in healthcare, and exhibit two key characteristics: intra-series irregularity and inter-series discrepancy.

Irregular Time Series Representation Learning +1

A Versatile Multi-Agent Reinforcement Learning Benchmark for Inventory Management

1 code implementation13 Jun 2023 Xianliang Yang, Zhihao Liu, Wei Jiang, Chuheng Zhang, Li Zhao, Lei Song, Jiang Bian

Multi-agent reinforcement learning (MARL) models multiple agents that interact and learn within a shared environment.

Autonomous Driving Management +3

Mildly Constrained Evaluation Policy for Offline Reinforcement Learning

1 code implementation6 Jun 2023 Linjie Xu, Zhengyao Jiang, Jinyu Wang, Lei Song, Jiang Bian

Offline reinforcement learning (RL) methodologies enforce constraints on the policy to adhere closely to the behavior policy, thereby stabilizing value learning and mitigating the selection of out-of-distribution (OOD) actions during test time.

D4RL MuJoCo +4

UADB: Unsupervised Anomaly Detection Booster

1 code implementation3 Jun 2023 Hangting Ye, Zhining Liu, Xinyi Shen, Wei Cao, Shun Zheng, Xiaofan Gui, Huishuai Zhang, Yi Chang, Jiang Bian

This is a challenging task given the heterogeneous model structures and assumptions adopted by existing UAD methods.

Unsupervised Anomaly Detection

MuseCoco: Generating Symbolic Music from Text

2 code implementations31 May 2023 Peiling Lu, Xin Xu, Chenfei Kang, Botao Yu, Chengyi Xing, Xu Tan, Jiang Bian

In contrast, symbolic music offers ease of editing, making it more accessible for users to manipulate specific musical elements.

Attribute Audio Generation +1

Deliberate then Generate: Enhanced Prompting Framework for Text Generation

no code implementations31 May 2023 Bei Li, Rui Wang, Junliang Guo, Kaitao Song, Xu Tan, Hany Hassan, Arul Menezes, Tong Xiao, Jiang Bian, Jingbo Zhu

Large language models (LLMs) have shown remarkable success across a wide range of natural language generation tasks, where proper prompt designs make great impacts.

Text Generation

GETMusic: Generating Any Music Tracks with a Unified Representation and Diffusion Framework

1 code implementation18 May 2023 Ang Lv, Xu Tan, Peiling Lu, Wei Ye, Shikun Zhang, Jiang Bian, Rui Yan

Our proposed representation, coupled with the non-autoregressive generative model, empowers GETMusic to generate music with any arbitrary source-target track combinations.

Denoising Music Generation

ResiDual: Transformer with Dual Residual Connections

1 code implementation28 Apr 2023 Shufang Xie, Huishuai Zhang, Junliang Guo, Xu Tan, Jiang Bian, Hany Hassan Awadalla, Arul Menezes, Tao Qin, Rui Yan

In this paper, we propose ResiDual, a novel Transformer architecture with Pre-Post-LN (PPLN), which fuses the connections in Post-LN and Pre-LN together and inherits their advantages while avoids their limitations.

Machine Translation

H-TSP: Hierarchically Solving the Large-Scale Travelling Salesman Problem

1 code implementation19 Apr 2023 Xuanhao Pan, Yan Jin, Yuandong Ding, Mingxiao Feng, Li Zhao, Lei Song, Jiang Bian

We propose an end-to-end learning framework based on hierarchical reinforcement learning, called H-TSP, for addressing the large-scale Travelling Salesman Problem (TSP).

Deep Reinforcement Learning Hierarchical Reinforcement Learning +1

Pointerformer: Deep Reinforced Multi-Pointer Transformer for the Traveling Salesman Problem

2 code implementations19 Apr 2023 Yan Jin, Yuandong Ding, Xuanhao Pan, Kun He, Li Zhao, Tao Qin, Lei Song, Jiang Bian

Traveling Salesman Problem (TSP), as a classic routing optimization problem originally arising in the domain of transportation and logistics, has become a critical task in broader domains, such as manufacturing and biology.

Decoder Deep Reinforcement Learning +1

NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizers

2 code implementations18 Apr 2023 Kai Shen, Zeqian Ju, Xu Tan, Yanqing Liu, Yichong Leng, Lei He, Tao Qin, Sheng Zhao, Jiang Bian

To enhance the zero-shot capability that is important to achieve diverse speech synthesis, we design a speech prompting mechanism to facilitate in-context learning in the diffusion model and the duration/pitch predictor.

In-Context Learning Speech Synthesis +2

Identifying Symptoms of Delirium from Clinical Narratives Using Natural Language Processing

no code implementations31 Mar 2023 Aokun Chen, Daniel Paredes, Zehao Yu, Xiwei Lou, Roberta Brunson, Jamie N. Thomas, Kimberly A. Martinez, Robert J. Lucero, Tanja Magoc, Laurence M. Solberg, Urszula A. Snigurska, Sarah E. Ser, Mattia Prosperi, Jiang Bian, Ragnhildur I. Bjarnadottir, Yonghui Wu

To assist in the diagnosis and phenotyping of delirium, we formed an expert panel to categorize diverse delirium symptoms, composed annotation guidelines, created a delirium corpus with diverse delirium symptoms, and developed NLP methods to extract delirium symptoms from clinical notes.

Language Modelling Large Language Model

DAE-Talker: High Fidelity Speech-Driven Talking Face Generation with Diffusion Autoencoder

no code implementations30 Mar 2023 Chenpeng Du, Qi Chen, Tianyu He, Xu Tan, Xie Chen, Kai Yu, Sheng Zhao, Jiang Bian

Additionally, we propose a novel method for generating continuous video frames with the DDIM image decoder trained on individual frames, eliminating the need for modelling the joint distribution of consecutive frames directly.

Decoder Talking Face Generation

Contextualized Medication Information Extraction Using Transformer-based Deep Learning Architectures

no code implementations14 Mar 2023 Aokun Chen, Zehao Yu, Xi Yang, Yi Guo, Jiang Bian, Yonghui Wu

Materials and methods: We developed NLP systems for medication mention extraction, event classification (indicating medication changes discussed or not), and context classification to classify medication changes context into 5 orthogonal dimensions related to drug changes.

Classification Deep Learning +3

Clinical Concept and Relation Extraction Using Prompt-based Machine Reading Comprehension

no code implementations14 Mar 2023 Cheng Peng, Xi Yang, Zehao Yu, Jiang Bian, William R. Hogan, Yonghui Wu

GatorTron-MRC achieves the best strict and lenient F1-scores for concept extraction, outperforming previous deep learning models on the two datasets by 1%~3% and 0. 7%~1. 3%, respectively.

Clinical Concept Extraction Machine Reading Comprehension +3

DR-VIDAL -- Doubly Robust Variational Information-theoretic Deep Adversarial Learning for Counterfactual Prediction and Treatment Effect Estimation on Real World Data

1 code implementation7 Mar 2023 Shantanu Ghosh, Zheng Feng, Jiang Bian, Kevin Butler, Mattia Prosperi

DR-VIDAL integrates: (i) a variational autoencoder (VAE) to factorize confounders into latent variables according to causal assumptions; (ii) an information-theoretic generative adversarial network (Info-GAN) to generate counterfactuals; (iii) a doubly robust block incorporating treatment propensities for outcome predictions.

counterfactual Generative Adversarial Network

Video4MRI: An Empirical Study on Brain Magnetic Resonance Image Analytics with CNN-based Video Classification Frameworks

no code implementations24 Feb 2023 Yuxuan Zhang, Qingzhong Wang, Jiang Bian, Yi Liu, Yanwu Xu, Dejing Dou, Haoyi Xiong

Due to the high similarity between MRI data and videos, we conduct extensive empirical studies on video recognition techniques for MRI classification to answer the questions: (1) can we directly use video recognition models for MRI classification, (2) which model is more appropriate for MRI, (3) are the common tricks like data augmentation in video recognition still useful for MRI classification?

Classification Data Augmentation +4

A Study on ReLU and Softmax in Transformer

no code implementations13 Feb 2023 Kai Shen, Junliang Guo, Xu Tan, Siliang Tang, Rui Wang, Jiang Bian

This paper sheds light on the following points: 1) Softmax and ReLU use different normalization methods over elements which lead to different variances of results, and ReLU is good at dealing with a large number of key-value slots; 2) FFN and key-value memory are equivalent, and thus the Transformer can be viewed as a memory network where FFNs and self-attention networks are both key-value memories.

Document Translation

Regeneration Learning: A Learning Paradigm for Data Generation

no code implementations21 Jan 2023 Xu Tan, Tao Qin, Jiang Bian, Tie-Yan Liu, Yoshua Bengio

Regeneration learning extends the concept of representation learning to data generation tasks, and can be regarded as a counterpart of traditional representation learning, since 1) regeneration learning handles the abstraction (Y') of the target data Y for data generation while traditional representation learning handles the abstraction (X') of source data X for data understanding; 2) both the processes of Y'-->Y in regeneration learning and X-->X' in representation learning can be learned in a self-supervised way (e. g., pre-training); 3) both the mappings from X to Y' in regeneration learning and from X' to Y in representation learning are simpler than the direct mapping from X to Y.

Image Generation Representation Learning +6

ResGrad: Residual Denoising Diffusion Probabilistic Models for Text to Speech

1 code implementation30 Dec 2022 Zehua Chen, Yihan Wu, Yichong Leng, Jiawei Chen, Haohe Liu, Xu Tan, Yang Cui, Ke Wang, Lei He, Sheng Zhao, Jiang Bian, Danilo Mandic

Denoising Diffusion Probabilistic Models (DDPMs) are emerging in text-to-speech (TTS) synthesis because of their strong capability of generating high-fidelity samples.

Denoising text-to-speech +1

Learning from Training Dynamics: Identifying Mislabeled Data Beyond Manually Designed Features

1 code implementation19 Dec 2022 Qingrui Jia, Xuhong LI, Lei Yu, Jiang Bian, Penghao Zhao, Shupeng Li, Haoyi Xiong, Dejing Dou

While mislabeled or ambiguously-labeled samples in the training set could negatively affect the performance of deep models, diagnosing the dataset and identifying mislabeled samples helps to improve the generalization power.

Empowering Diffusion Models on the Embedding Space for Text Generation

1 code implementation19 Dec 2022 Zhujin Gao, Junliang Guo, Xu Tan, Yongxin Zhu, Fang Zhang, Jiang Bian, Linli Xu

Diffusion models have achieved state-of-the-art synthesis quality on both visual and audio tasks, and recent works further adapt them to textual data by diffusing on the embedding space.

Denoising Machine Translation +2

Multi-Agent Reinforcement Learning with Shared Resources for Inventory Management

no code implementations15 Dec 2022 Yuandong Ding, Mingxiao Feng, Guozi Liu, Wei Jiang, Chuheng Zhang, Li Zhao, Lei Song, Houqiang Li, Yan Jin, Jiang Bian

In this paper, we consider the inventory management (IM) problem where we need to make replenishment decisions for a large number of stock keeping units (SKUs) to balance their supply and demand.

Management Multi-agent Reinforcement Learning +3

SODA: A Natural Language Processing Package to Extract Social Determinants of Health for Cancer Studies

no code implementations6 Dec 2022 Zehao Yu, Xi Yang, Chong Dang, Prakash Adekkanattu, Braja Gopal Patra, Yifan Peng, Jyotishman Pathak, Debbie L. Wilson, Ching-Yuan Chang, Wei-Hsuan Lo-Ciganic, Thomas J. George, William R. Hogan, Yi Guo, Jiang Bian, Yonghui Wu

Objective: We aim to develop an open-source natural language processing (NLP) package, SODA (i. e., SOcial DeterminAnts), with pre-trained transformer models to extract social determinants of health (SDoH) for cancer patients, examine the generalizability of SODA to a new disease domain (i. e., opioid use), and evaluate the extraction rate of SDoH using cancer populations.

TD3 with Reverse KL Regularizer for Offline Reinforcement Learning from Mixed Datasets

1 code implementation5 Dec 2022 Yuanying Cai, Chuheng Zhang, Li Zhao, Wei Shen, Xuyun Zhang, Lei Song, Jiang Bian, Tao Qin, TieYan Liu

There are two challenges for this setting: 1) The optimal trade-off between optimizing the RL signal and the behavior cloning (BC) signal changes on different states due to the variation of the action coverage induced by different behavior policies.

D4RL MuJoCo +3

Exploring the Limits of Differentially Private Deep Learning with Group-wise Clipping

no code implementations3 Dec 2022 Jiyan He, Xuechen Li, Da Yu, Huishuai Zhang, Janardhan Kulkarni, Yin Tat Lee, Arturs Backurs, Nenghai Yu, Jiang Bian

To reduce the compute time overhead of private learning, we show that \emph{per-layer clipping}, where the gradient of each neural network layer is clipped separately, allows clipping to be performed in conjunction with backpropagation in differentially private optimization.

Computational Efficiency

VideoDubber: Machine Translation with Speech-Aware Length Control for Video Dubbing

1 code implementation30 Nov 2022 Yihan Wu, Junliang Guo, Xu Tan, Chen Zhang, Bohan Li, Ruihua Song, Lei He, Sheng Zhao, Arul Menezes, Jiang Bian

In this paper, we propose a machine translation system tailored for the task of video dubbing, which directly considers the speech duration of each token in translation, to match the length of source and target speech.

Machine Translation Sentence +4

Multi-Objective Personalized Product Retrieval in Taobao Search

no code implementations9 Oct 2022 Yukun Zheng, Jiang Bian, Guanghao Meng, Chao Zhang, Honggang Wang, Zhixuan Zhang, Sen Li, Tao Zhuang, Qingwen Liu, Xiaoyi Zeng

These problems promote us to further strengthen the capabilities of our EBR model in both relevance estimation and personalized retrieval.

Collaborative Filtering Retrieval

Learning Differential Operators for Interpretable Time Series Modeling

no code implementations3 Sep 2022 Yingtao Luo, Chang Xu, Yang Liu, Weiqing Liu, Shun Zheng, Jiang Bian

In this work, we propose an learning framework that can automatically obtain interpretable PDE models from sequential data.

Decision Making Meta-Learning +2

AA-Forecast: Anomaly-Aware Forecast for Extreme Events

9 code implementations21 Aug 2022 Ashkan Farhangi, Jiang Bian, Arthur Huang, Haoyi Xiong, Jun Wang, Zhishan Guo

Moreover, the framework employs a dynamic uncertainty optimization algorithm that reduces the uncertainty of forecasts in an online manner.

Anomaly Forecasting Multivariate Time Series Forecasting +5

P2ANet: A Dataset and Benchmark for Dense Action Detection from Table Tennis Match Broadcasting Videos

no code implementations26 Jul 2022 Jiang Bian, Xuhong LI, Tao Wang, Qingzhong Wang, Jun Huang, Chen Liu, Jun Zhao, Feixiang Lu, Dejing Dou, Haoyi Xiong

While deep learning has been widely used for video analytics, such as video classification and action detection, dense action detection with fast-moving subjects from sports videos is still challenging.

Action Detection Action Localization +2

Variational Temporal Deconfounder for Individualized Treatment Effect Estimation from Longitudinal Observational Data

no code implementations23 Jul 2022 Zheng Feng, Mattia Prosperi, Jiang Bian

Estimating treatment effects, especially individualized treatment effects (ITE), using observational data is challenging due to the complex situations of confounding bias.

LordNet: An Efficient Neural Network for Learning to Solve Parametric Partial Differential Equations without Simulated Data

no code implementations19 Jun 2022 Xinquan Huang, Wenlei Shi, Xiaotian Gao, Xinran Wei, Jia Zhang, Jiang Bian, Mao Yang, Tie-Yan Liu

We investigate the physical information in the MSR loss, which we called long-range entanglements, and identify the challenge that the neural network requires the capacity to model the long-range entanglements in the spatial domain of the PDE, whose patterns vary in different PDEs.

Efficient Neural Network

MoESys: A Distributed and Efficient Mixture-of-Experts Training and Inference System for Internet Services

1 code implementation20 May 2022 dianhai yu, Liang Shen, Hongxiang Hao, Weibao Gong, HuaChao Wu, Jiang Bian, LiRong Dai, Haoyi Xiong

For scalable inference in a single node, especially when the model size is larger than GPU memory, MoESys builds the CPU-GPU memory jointly into a ring of sections to load the model, and executes the computation tasks across the memory sections in a round-robin manner for efficient inference.

Distributed Computing Mixture-of-Experts

A Simple yet Effective Framework for Active Learning to Rank

no code implementations20 May 2022 Qingzhong Wang, Haifang Li, Haoyi Xiong, Wen Wang, Jiang Bian, Yu Lu, Shuaiqiang Wang, Zhicong Cheng, Dejing Dou, Dawei Yin

To handle the diverse query requests from users at web-scale, Baidu has done tremendous efforts in understanding users' queries, retrieve relevant contents from a pool of trillions of webpages, and rank the most relevant webpages on the top of results.

Active Learning Learning-To-Rank

Towards Applicable Reinforcement Learning: Improving the Generalization and Sample Efficiency with Policy Ensemble

no code implementations19 May 2022 Zhengyu Yang, Kan Ren, Xufang Luo, Minghuan Liu, Weiqing Liu, Jiang Bian, Weinan Zhang, Dongsheng Li

Considering the great performance of ensemble methods on both accuracy and generalization in supervised learning (SL), we design a robust and applicable method named Ensemble Proximal Policy Optimization (EPPO), which learns ensemble policies in an end-to-end manner.

Diversity reinforcement-learning +1

DEPTS: Deep Expansion Learning for Periodic Time Series Forecasting

1 code implementation ICLR 2022 Wei Fan, Shun Zheng, Xiaohan Yi, Wei Cao, Yanjie Fu, Jiang Bian, Tie-Yan Liu

However, the complicated dependencies of the PTS signal on its inherent periodicity as well as the sophisticated composition of various periods hinder the performance of PTS forecasting.

Scheduling Time Series +1

Dynamic Relation Discovery and Utilization in Multi-Entity Time Series Forecasting

no code implementations18 Feb 2022 Lin Huang, Lijun Wu, Jia Zhang, Jiang Bian, Tie-Yan Liu

How to discover the useful implicit relation between entities and effectively utilize the relations for each entity under various circumstances is crucial.

Graph Learning Graph Neural Network +3

Learning Physics-Informed Neural Networks without Stacked Back-propagation

1 code implementation18 Feb 2022 Di He, Shanda Li, Wenlei Shi, Xiaotian Gao, Jia Zhang, Jiang Bian, LiWei Wang, Tie-Yan Liu

In this work, we develop a novel approach that can significantly accelerate the training of Physics-Informed Neural Networks.

AF$_2$: Adaptive Focus Framework for Aerial Imagery Segmentation

no code implementations18 Feb 2022 Lin Huang, Qiyuan Dong, Lijun Wu, Jia Zhang, Jiang Bian, Tie-Yan Liu

As a specific semantic segmentation task, aerial imagery segmentation has been widely employed in high spatial resolution (HSR) remote sensing images understanding.

Segmentation Semantic Segmentation

GatorTron: A Large Clinical Language Model to Unlock Patient Information from Unstructured Electronic Health Records

no code implementations2 Feb 2022 Xi Yang, Aokun Chen, Nima PourNejatian, Hoo Chang Shin, Kaleb E Smith, Christopher Parisien, Colin Compas, Cheryl Martin, Mona G Flores, Ying Zhang, Tanja Magoc, Christopher A Harle, Gloria Lipori, Duane A Mitchell, William R Hogan, Elizabeth A Shenkman, Jiang Bian, Yonghui Wu

GatorTron models scale up the clinical language model from 110 million to 8. 9 billion parameters and improve 5 clinical NLP tasks (e. g., 9. 6% and 9. 5% improvement in accuracy for NLI and MQA), which can be applied to medical AI systems to improve healthcare delivery.

Clinical Concept Extraction Language Modeling +7

DDG-DA: Data Distribution Generation for Predictable Concept Drift Adaptation

1 code implementation11 Jan 2022 Wendi Li, Xiao Yang, Weiqing Liu, Yingce Xia, Jiang Bian

To handle concept drift, previous methods first detect when/where the concept drift happens and then adapt models to fit the distribution of the latest data.

Stock Prediction

SHGNN: Structure-Aware Heterogeneous Graph Neural Network

1 code implementation12 Dec 2021 Wentao Xu, Yingce Xia, Weiqing Liu, Jiang Bian, Jian Yin, Tie-Yan Liu

Next, we use a tree-attention aggregator to incorporate the graph structure information into the aggregation module on the meta-path.

Graph Embedding Graph Neural Network +1

KGE-CL: Contrastive Learning of Tensor Decomposition Based Knowledge Graph Embeddings

2 code implementations COLING 2022 Zhiping Luo, Wentao Xu, Weiqing Liu, Jiang Bian, Jian Yin, Tie-Yan Liu

Learning the embeddings of knowledge graphs (KG) is vital in artificial intelligence, and can benefit various downstream applications, such as recommendation and question answering.

Contrastive Learning Knowledge Graph Embedding +7

HIST: A Graph-based Framework for Stock Trend Forecasting via Mining Concept-Oriented Shared Information

2 code implementations26 Oct 2021 Wentao Xu, Weiqing Liu, Lewen Wang, Yingce Xia, Jiang Bian, Jian Yin, Tie-Yan Liu

To overcome the shortcomings of previous work, we proposed a novel stock trend forecasting framework that can adequately mine the concept-oriented shared information from predefined concepts and hidden concepts.

Deep Ensemble Policy Learning

no code implementations29 Sep 2021 Zhengyu Yang, Kan Ren, Xufang Luo, Weiqing Liu, Jiang Bian, Weinan Zhang, Dongsheng Li

Ensemble learning, which can consistently improve the prediction performance in supervised learning, has drawn increasing attentions in reinforcement learning (RL).

Diversity Ensemble Learning +1

Multi-Agent Reinforcement Learning with Shared Resource in Inventory Management

no code implementations29 Sep 2021 Mingxiao Feng, Guozi Liu, Li Zhao, Lei Song, Jiang Bian, Tao Qin, Wengang Zhou, Houqiang Li, Tie-Yan Liu

We consider inventory management (IM) problem for a single store with a large number of SKUs (stock keeping units) in this paper, where we need to make replenishment decisions for each SKU to balance its supply and demand.

Management Multi-agent Reinforcement Learning +3

Instance-wise Graph-based Framework for Multivariate Time Series Forecasting

1 code implementation14 Sep 2021 Wentao Xu, Weiqing Liu, Jiang Bian, Jian Yin, Tie-Yan Liu

In this paper, we propose a simple yet efficient instance-wise graph-based framework to utilize the inter-dependencies of different variables at different time stamps for multivariate time series forecasting.

Multivariate Time Series Forecasting Time Series

Explaining Algorithmic Fairness Through Fairness-Aware Causal Path Decomposition

no code implementations11 Aug 2021 Weishen Pan, Sen Cui, Jiang Bian, ChangShui Zhang, Fei Wang

Algorithmic fairness has aroused considerable interests in data mining and machine learning communities recently.

Attribute Fairness +1

A Study of Social and Behavioral Determinants of Health in Lung Cancer Patients Using Transformers-based Natural Language Processing Models

no code implementations10 Aug 2021 Zehao Yu, Xi Yang, Chong Dang, Songzi Wu, Prakash Adekkanattu, Jyotishman Pathak, Thomas J. George, William R. Hogan, Yi Guo, Jiang Bian, Yonghui Wu

In this study, we examined two state-of-the-art transformer-based NLP models, including BERT and RoBERTa, to extract SBDoH concepts from clinical narratives, applied the best performing model to extract SBDoH concepts on a lung cancer screening patient cohort, and examined the difference of SBDoH information between NLP extracted results and structured EHRs (SBDoH information captured in standard vocabularies such as the International Classification of Diseases codes).

Clinical Relation Extraction Using Transformer-based Models

1 code implementation19 Jul 2021 Xi Yang, Zehao Yu, Yi Guo, Jiang Bian, Yonghui Wu

The goal of this study is to systematically explore three widely used transformer-based models (i. e., BERT, RoBERTa, and XLNet) for clinical relation extraction and develop an open-source package with clinical pre-trained transformer-based models to facilitate information extraction in the clinical domain.

Binary Classification Multi-class Classification +2

Deep Risk Model: A Deep Learning Solution for Mining Latent Risk Factors to Improve Covariance Matrix Estimation

1 code implementation12 Jul 2021 Hengxu Lin, Dong Zhou, Weiqing Liu, Jiang Bian

Modeling and managing portfolio risk is perhaps the most important step to achieve growing and preserving investment performance.

Assessing putative bias in prediction of anti-microbial resistance from real-world genotyping data under explicit causal assumptions

no code implementations6 Jul 2021 Mattia Prosperi, Simone Marini, Christina Boucher, Jiang Bian

Whole genome sequencing (WGS) is quickly becoming the customary means for identification of antimicrobial resistance (AMR) due to its ability to obtain high resolution information about the genes and mechanisms that are causing resistance and driving pathogen mobility.

Learning Multiple Stock Trading Patterns with Temporal Routing Adaptor and Optimal Transport

1 code implementation24 Jun 2021 Hengxu Lin, Dong Zhou, Weiqing Liu, Jiang Bian

In this paper, we propose a novel architecture, Temporal Routing Adaptor (TRA), to empower existing stock prediction models with the ability to model multiple stock trading patterns.

Stock Prediction

Deep Learning Models in Detection of Dietary Supplement Adverse Event Signals from Twitter

no code implementations21 Jun 2021 Yefeng Wang, Yunpeng Zhao, Jiang Bian, Rui Zhang

We chose the best performing models in each task to assemble an end-to-end deep learning pipeline to detect DS AE signals and compared the results to the known DS AEs from a DS knowledge base (i. e., iDISK).

Deep Learning Relation Extraction +1

Deep Subdomain Adaptation Network for Image Classification

1 code implementation17 Jun 2021 Yongchun Zhu, Fuzhen Zhuang, Jindong Wang, Guolin Ke, Jingwu Chen, Jiang Bian, Hui Xiong, Qing He

The adaptation can be achieved easily with most feed-forward network models by extending them with LMMD loss, which can be trained efficiently via back-propagation.

Classification Domain Adaptation +5

Impact of pandemic fatigue on the spread of COVID-19: a mathematical modelling study

no code implementations9 Apr 2021 Disheng Tang, Wei Cao, Jiang Bian, Tie-Yan Liu, Zhifeng Gao, Shun Zheng, Jue Liu

We used a stochastic metapopulation model with a hierarchical structure and fitted the model to the positive cases in the US from the start of outbreak to the end of 2020.

A Conversational Agent System for Dietary Supplements Use

no code implementations4 Apr 2021 Esha Singh, Anu Bompelli, Ruyuan Wan, Jiang Bian, Serguei Pakhomov, Rui Zhang

Dietary supplements (DS) have been widely used by consumers, but the information around the efficacy and safety of DS is disparate or incomplete, thus creating barriers for consumers to find information effectively.

Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyond

1 code implementation19 Mar 2021 Xuhong LI, Haoyi Xiong, Xingjian Li, Xuanyu Wu, Xiao Zhang, Ji Liu, Jiang Bian, Dejing Dou

Then, to understand the interpretation results, we also survey the performance metrics for evaluating interpretation algorithms.

Adversarial Robustness Deep Learning +1

REST: Relational Event-driven Stock Trend Forecasting

no code implementations15 Feb 2021 Wentao Xu, Weiqing Liu, Chang Xu, Jiang Bian, Jian Yin, Tie-Yan Liu

To remedy the first shortcoming, we propose to model the stock context and learn the effect of event information on the stocks under different contexts.

Universal Trading for Order Execution with Oracle Policy Distillation

no code implementations28 Jan 2021 Yuchen Fang, Kan Ren, Weiqing Liu, Dong Zhou, Weinan Zhang, Jiang Bian, Yong Yu, Tie-Yan Liu

As a fundamental problem in algorithmic trading, order execution aims at fulfilling a specific trading order, either liquidation or acquirement, for a given instrument.

Algorithmic Trading reinforcement-learning +2

Applications of artificial intelligence in drug development using real-world data

no code implementations22 Jan 2021 Zhaoyi Chen, Xiong Liu, William Hogan, Elizabeth Shenkman, Jiang Bian

The US Food and Drug Administration (FDA) has been actively promoting the use of real-world data (RWD) in drug development.

Event Detection

Dynamic Graph Representation Learning with Fourier Temporal State Embedding

1 code implementation1 Jan 2021 Yihan He, Wei Cao, Shun Zheng, Zhifeng Gao, Jiang Bian

In this work, we present a new method named Fourier Temporal State Embedding (FTSE) to address the temporal information in dynamic graph representation learning.

Graph Embedding Graph Representation Learning

LINGUINE: LearnIng to pruNe on subGraph convolUtIon NEtworks

no code implementations1 Jan 2021 Yihan He, Wei Cao, Shun Zheng, Zhifeng Gao, Jiang Bian

In recent years, research communities have been developing stochastic sampling methods to handle large graphs when it is unreal to put the whole graph into a single batch.

Graph Representation Learning

Cooperative Policy Learning with Pre-trained Heterogeneous Observation Representations

1 code implementation24 Dec 2020 Wenlei Shi, Xinran Wei, Jia Zhang, Xiaoyuan Ni, Arthur Jiang, Jiang Bian, Tie-Yan Liu

While adopting complex GNN models with more informative message passing and aggregation mechanisms can obviously benefit heterogeneous vertex representations and cooperative policy learning, it could, on the other hand, increase the training difficulty of MARL and demand more intense and direct reward signals compared to the original global reward.

Decoder Graph Attention +1

ADD: Augmented Disentanglement Distillation Framework for Improving Stock Trend Forecasting

1 code implementation11 Dec 2020 Hongshun Tang, Lijun Wu, Weiqing Liu, Jiang Bian

Stock trend forecasting has become a popular research direction that attracts widespread attention in the financial field.

Decoder Disentanglement

COSEA: Convolutional Code Search with Layer-wise Attention

no code implementations19 Oct 2020 Hao Wang, Jia Zhang, Yingce Xia, Jiang Bian, Chao Zhang, Tie-Yan Liu

However, most existing studies overlook the code's intrinsic structural logic, which indeed contains a wealth of semantic information, and fails to capture intrinsic features of codes.

Code Search

MESA: Boost Ensemble Imbalanced Learning with MEta-SAmpler

2 code implementations NeurIPS 2020 Zhining Liu, Pengfei Wei, Jing Jiang, Wei Cao, Jiang Bian, Yi Chang

This makes MESA generally applicable to most of the existing learning models and the meta-sampler can be efficiently applied to new tasks.

imbalanced classification Meta-Learning

Qlib: An AI-oriented Quantitative Investment Platform

2 code implementations22 Sep 2020 Xiao Yang, Weiqing Liu, Dong Zhou, Jiang Bian, Tie-Yan Liu

Quantitative investment aims to maximize the return and minimize the risk in a sequential trading period over a set of financial instruments.

Portfolio Optimization Stock Market Prediction

Learning to Reweight with Deep Interactions

no code implementations9 Jul 2020 Yang Fan, Yingce Xia, Lijun Wu, Shufang Xie, Weiqing Liu, Jiang Bian, Tao Qin, Xiang-Yang Li

Recently, the concept of teaching has been introduced into machine learning, in which a teacher model is used to guide the training of a student model (which will be used in real tasks) through data selection, loss function design, etc.

image-classification Image Classification +2

Measuring Model Complexity of Neural Networks with Curve Activation Functions

no code implementations16 Jun 2020 Xia Hu, Weiqing Liu, Jiang Bian, Jian Pei

Our results demonstrate that the occurrence of overfitting is positively correlated with the increase of model complexity during training.

MC-BERT: Efficient Language Pre-Training via a Meta Controller

1 code implementation10 Jun 2020 Zhenhui Xu, Linyuan Gong, Guolin Ke, Di He, Shuxin Zheng, Li-Wei Wang, Jiang Bian, Tie-Yan Liu

Pre-trained contextual representations (e. g., BERT) have become the foundation to achieve state-of-the-art results on many NLP tasks.

Binary Classification Cloze Test +5

Invertible Image Rescaling

11 code implementations ECCV 2020 Mingqing Xiao, Shuxin Zheng, Chang Liu, Yaolong Wang, Di He, Guolin Ke, Jiang Bian, Zhouchen Lin, Tie-Yan Liu

High-resolution digital images are usually downscaled to fit various display screens or save the cost of storage and bandwidth, meanwhile the post-upscaling is adpoted to recover the original resolutions or the details in the zoom-in images.

Image Rescaling Image Super-Resolution

Integrating Crowdsourcing and Active Learning for Classification of Work-Life Events from Tweets

no code implementations26 Mar 2020 Yunpeng Zhao, Mattia Prosperi, Tianchen Lyu, Yi Guo, Jiang Bian

Results show that crowdsourcing is useful to create high-quality annotations and active learning helps in reducing the number of required tweets, although there was no substantial difference among the strategies tested.

Active Learning General Classification

Federated Learning for Healthcare Informatics

no code implementations13 Nov 2019 Jie Xu, Benjamin S. Glicksberg, Chang Su, Peter Walker, Jiang Bian, Fei Wang

With the rapid development of computer software and hardware technologies, more and more healthcare data are becoming readily available from clinical institutions, patients, insurance companies and pharmaceutical industries, among others.

Federated Learning

Fully Parameterized Quantile Function for Distributional Reinforcement Learning

6 code implementations NeurIPS 2019 Derek Yang, Li Zhao, Zichuan Lin, Tao Qin, Jiang Bian, Tie-Yan Liu

The key challenge in practical distributional RL algorithms lies in how to parameterize estimated distributions so as to better approximate the true continuous distribution.

Ranked #3 on Atari Games on Atari 2600 Skiing (using extra training data)

Atari Games Distributional Reinforcement Learning +3

Identifying Cancer Patients at Risk for Heart Failure Using Machine Learning Methods

no code implementations1 Oct 2019 Xi Yang, Yan Gong, Nida Waheed, Keith March, Jiang Bian, William R. Hogan, Yonghui Wu

Early detection of cancer patients at risk for cardiotoxicity before cardiotoxic treatments and providing preventive measures are potential solutions to improve cancer patients's quality of life.

BIG-bench Machine Learning Specificity

Demonstration Actor Critic

no code implementations25 Sep 2019 Guoqing Liu, Li Zhao, Pushi Zhang, Jiang Bian, Tao Qin, Nenghai Yu, Tie-Yan Liu

One approach leverages demonstration data in a supervised manner, which is simple and direct, but can only provide supervision signal over those states seen in the demonstrations.

Independence-aware Advantage Estimation

no code implementations25 Sep 2019 Pushi Zhang, Li Zhao, Guoqing Liu, Jiang Bian, Minglie Huang, Tao Qin, Tie-Yan Liu

Most of existing advantage function estimation methods in reinforcement learning suffer from the problem of high variance, which scales unfavorably with the time horizon.

Self-paced Ensemble for Highly Imbalanced Massive Data Classification

1 code implementation8 Sep 2019 Zhining Liu, Wei Cao, Zhifeng Gao, Jiang Bian, Hechang Chen, Yi Chang, Tie-Yan Liu

To tackle this problem, we conduct deep investigations into the nature of class imbalance, which reveals that not only the disproportion between classes, but also other difficulties embedded in the nature of data, especially, noises and class overlapping, prevent us from learning effective classifiers.

Classification General Classification +1

LightMC: A Dynamic and Efficient Multiclass Decomposition Algorithm

no code implementations25 Aug 2019 Ziyu Liu, Guolin Ke, Jiang Bian, Tie-Yan Liu

Instead of using fixed coding matrix and decoding strategy, LightMC uses a differentiable decoding strategy, which enables it to dynamically optimize the coding matrix and decoding strategy, toward increasing the overall accuracy of multiclass classification, via back propagation jointly with the training of base learners in an iterative way.

Classification General Classification

Cannot find the paper you are looking for? You can Submit a new open access paper.