Search Results for author: Yuan YAO

Found 134 papers, 66 papers with code

dS^2LBI: Exploring Structural Sparsity on Deep Network via Differential Inclusion Paths

no code implementations ICML 2020 Yanwei Fu, Chen Liu, Donghao Li, Xinwei Sun, Jinshan Zeng, Yuan YAO

Over-parameterization is ubiquitous nowadays in training neural networks to benefit both optimization in seeking global optima and generalization in reducing prediction error.

CodRED: A Cross-Document Relation Extraction Dataset for Acquiring Knowledge in the Wild

1 code implementation EMNLP 2021 Yuan YAO, Jiaju Du, Yankai Lin, Peng Li, Zhiyuan Liu, Jie zhou, Maosong Sun

Existing relation extraction (RE) methods typically focus on extracting relational facts between entity pairs within single sentences or documents.

Relation Relation Extraction

LLaVA-UHD: an LMM Perceiving Any Aspect Ratio and High-Resolution Images

1 code implementation18 Mar 2024 Ruyi Xu, Yuan YAO, Zonghao Guo, Junbo Cui, Zanlin Ni, Chunjiang Ge, Tat-Seng Chua, Zhiyuan Liu, Maosong Sun, Gao Huang

To address the challenges, we present LLaVA-UHD, a large multimodal model that can efficiently perceive images in any aspect ratio and high resolution.

MoleculeQA: A Dataset to Evaluate Factual Accuracy in Molecular Comprehension

1 code implementation13 Mar 2024 Xingyu Lu, He Cao, Zijing Liu, Shengyuan Bai, Leqing Chen, Yuan YAO, Hai-Tao Zheng, Yu Li

Large language models are playing an increasingly significant role in molecular research, yet existing models often generate erroneous information, posing challenges to accurate molecular comprehension.

Question Answering

Softened Symbol Grounding for Neuro-symbolic Systems

1 code implementation1 Mar 2024 Zenan Li, Yuan YAO, Taolue Chen, Jingwei Xu, Chun Cao, Xiaoxing Ma, Jian Lü

Neuro-symbolic learning generally consists of two separated worlds, i. e., neural network training and symbolic constraint solving, whose success hinges on symbol grounding, a fundamental problem in AI.

Learning with Logical Constraints but without Shortcut Satisfaction

1 code implementation1 Mar 2024 Zenan Li, Zehua Liu, Yuan YAO, Jingwei Xu, Taolue Chen, Xiaoxing Ma, Jian Lü

In this paper, we present a new framework for learning with logical constraints.

Evaluating Membership Inference Attacks and Defenses in Federated Learning

1 code implementation9 Feb 2024 Gongxi Zhu, Donghao Li, Hanlin Gu, Yuxing Han, Yuan YAO, Lixin Fan, Qiang Yang

Firstly, combining model information from multiple communication rounds (Multi-temporal) enhances the overall effectiveness of MIAs compared to utilizing model information from a single epoch.

Federated Learning

CoCoT: Contrastive Chain-of-Thought Prompting for Large Multimodal Models with Multiple Image Inputs

no code implementations5 Jan 2024 Daoan Zhang, Junming Yang, Hanjia Lyu, Zijian Jin, Yuan YAO, Mingkai Chen, Jiebo Luo

When exploring the development of Artificial General Intelligence (AGI), a critical task for these models involves interpreting and processing information from multiple image inputs.

Image Comprehension Text Matching +1

ASC: Adaptive Scale Feature Map Compression for Deep Neural Network

no code implementations13 Dec 2023 Yuan YAO, Tian-Sheuan Chang

Furthermore, the hardware architecture scales effectively, with only a sublinear increase in area cost.

DreaMoving: A Human Video Generation Framework based on Diffusion Models

no code implementations8 Dec 2023 Mengyang Feng, Jinlin Liu, Kai Yu, Yuan YAO, Zheng Hui, Xiefan Guo, Xianhui Lin, Haolan Xue, Chen Shi, Xiaowen Li, Aojie Li, Xiaoyang Kang, Biwen Lei, Miaomiao Cui, Peiran Ren, Xuansong Xie

In this paper, we present DreaMoving, a diffusion-based controllable video generation framework to produce high-quality customized human videos.

Video Generation

RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback

2 code implementations1 Dec 2023 Tianyu Yu, Yuan YAO, Haoye Zhang, Taiwen He, Yifeng Han, Ganqu Cui, Jinyi Hu, Zhiyuan Liu, Hai-Tao Zheng, Maosong Sun, Tat-Seng Chua

Multimodal Large Language Models (MLLMs) have recently demonstrated impressive capabilities in multimodal understanding, reasoning, and interaction.

Hallucination

InstructMol: Multi-Modal Integration for Building a Versatile and Reliable Molecular Assistant in Drug Discovery

1 code implementation27 Nov 2023 He Cao, Zijing Liu, Xingyu Lu, Yuan YAO, Yu Li

The rapid evolution of artificial intelligence in drug discovery encounters challenges with generalization and extensive training, yet Large Language Models (LLMs) offer promise in reshaping interactions with complex molecular data.

Drug Discovery Molecule Captioning

Advancing Transformer Architecture in Long-Context Large Language Models: A Comprehensive Survey

1 code implementation21 Nov 2023 Yunpeng Huang, Jingwei Xu, Junyu Lai, Zixu Jiang, Taolue Chen, Zenan Li, Yuan YAO, Xiaoxing Ma, Lijuan Yang, Hao Chen, Shupeng Li, Penghao Zhao

Transformer-based Large Language Models (LLMs) have been applied in diverse areas such as knowledge bases, human interfaces, and dynamic agents, and marking a stride towards achieving Artificial General Intelligence (AGI).

Navigate

NExT-Chat: An LMM for Chat, Detection and Segmentation

1 code implementation8 Nov 2023 Ao Zhang, Yuan YAO, Wei Ji, Zhiyuan Liu, Tat-Seng Chua

The development of large language models (LLMs) has greatly advanced the field of multimodal understanding, leading to the emergence of large multimodal models (LMMs).

Referring Expression Referring Expression Segmentation +1

Thoroughly Modeling Multi-domain Pre-trained Recommendation as Language

no code implementations20 Oct 2023 Zekai Qu, Ruobing Xie, Chaojun Xiao, Yuan YAO, Zhiyuan Liu, Fengzong Lian, Zhanhui Kang, Jie zhou

With the thriving of pre-trained language model (PLM) widely verified in various of NLP tasks, pioneer efforts attempt to explore the possible cooperation of the general textual information in PLM with the personalized behavioral information in user historical behavior sequences to enhance sequential recommendation (SR).

Informativeness Language Modelling +1

Reformulating Vision-Language Foundation Models and Datasets Towards Universal Multimodal Assistants

2 code implementations1 Oct 2023 Tianyu Yu, Jinyi Hu, Yuan YAO, Haoye Zhang, Yue Zhao, Chongyi Wang, Shan Wang, Yinxv Pan, Jiao Xue, Dahai Li, Zhiyuan Liu, Hai-Tao Zheng, Maosong Sun

The capabilities of MLLMs depend on two crucial factors: the model architecture to facilitate the feature alignment of visual modules and large language models; the multimodal instruction tuning datasets for human instruction following.

Instruction Following

On the Sweet Spot of Contrastive Views for Knowledge-enhanced Recommendation

no code implementations23 Sep 2023 Haibo Ye, Xinjie Li, Yuan YAO, Hanghang Tong

In recommender systems, knowledge graph (KG) can offer critical information that is lacking in the original user-item interaction graph (IG).

Contrastive Learning Recommendation Systems

Mitigating the Alignment Tax of RLHF

no code implementations12 Sep 2023 Yong Lin, Hangyu Lin, Wei Xiong, Shizhe Diao, Jianmeng Liu, Jipeng Zhang, Rui Pan, Haoxiang Wang, Wenbin Hu, Hanning Zhang, Hanze Dong, Renjie Pi, Han Zhao, Nan Jiang, Heng Ji, Yuan YAO, Tong Zhang

Building on the analysis and the observation that averaging different layers of the transformer leads to significantly different reward-tax trade-offs, we propose Adaptive Model Averaging (AMA) to adaptively find various combination ratios of model layers.

Common Sense Reasoning Continual Learning

Optimal Sample Selection Through Uncertainty Estimation and Its Application in Deep Learning

no code implementations5 Sep 2023 Yong Lin, Chen Liu, Chenlu Ye, Qing Lian, Yuan YAO, Tong Zhang

Our proposed method, COPS (unCertainty based OPtimal Sub-sampling), is designed to minimize the expected loss of a model trained on subsampled data.

Active Learning

FaceChain: A Playground for Human-centric Artificial Intelligence Generated Content

1 code implementation28 Aug 2023 Yang Liu, Cheng Yu, Lei Shang, Yongyi He, Ziheng Wu, Xingjun Wang, Chao Xu, Haoyu Xie, Weida Wang, Yuze Zhao, Lin Zhu, Chen Cheng, Weitao Chen, Yuan YAO, Wenmeng Zhou, Jiaqi Xu, Qiang Wang, Yingda Chen, Xuansong Xie, Baigui Sun

In this paper, we present FaceChain, a personalized portrait generation framework that combines a series of customized image-generation model and a rich set of face-related perceptual understanding models (\eg, face detection, deep face embedding extraction, and facial attribute recognition), to tackle aforementioned challenges and to generate truthful personalized portraits, with only a handful of portrait images as input.

Attribute Potrait Generation +1

Large Multilingual Models Pivot Zero-Shot Multimodal Learning across Languages

2 code implementations23 Aug 2023 Jinyi Hu, Yuan YAO, Chongyi Wang, Shan Wang, Yinxu Pan, Qianyu Chen, Tianyu Yu, Hanghao Wu, Yue Zhao, Haoye Zhang, Xu Han, Yankai Lin, Jiao Xue, Dahai Li, Zhiyuan Liu, Maosong Sun

Building a competitive counterpart in other languages is highly challenging due to the low-resource nature of non-English multimodal data (i. e., lack of large-scale, high-quality image-text data).

Language Modelling Large Language Model +1

Leveraging Side Information for Ligand Conformation Generation using Diffusion-Based Approaches

no code implementations2 Aug 2023 Jiamin Wu, He Cao, Yuan YAO

Examples of such side information include the chemical and geometric features of the target protein, ligand-target compound interactions, and ligand chemical properties.

Denoising Drug Discovery

Random Smoothing Regularization in Kernel Gradient Descent Learning

no code implementations5 May 2023 Liang Ding, Tianyang Hu, Jiahang Jiang, Donghao Li, Wenjia Wang, Yuan YAO

In this paper, we aim to bridge this gap by presenting a framework for random smoothing regularization that can adaptively and effectively learn a wide range of ground truth functions belonging to the classical Sobolev spaces.

Data Augmentation

VPGTrans: Transfer Visual Prompt Generator across LLMs

1 code implementation NeurIPS 2023 Ao Zhang, Hao Fei, Yuan YAO, Wei Ji, Li Li, Zhiyuan Liu, Tat-Seng Chua

While developing a new multimodal LLM (MLLM) by pre-training on tremendous image-text pairs from scratch can be exceedingly resource-consuming, connecting an existing LLM with a comparatively lightweight visual prompt generator (VPG) becomes a feasible paradigm.

Transfer Learning

Inducing Neural Collapse in Deep Long-tailed Learning

1 code implementation24 Feb 2023 Xuantong Liu, Jianfeng Zhang, Tianyang Hu, He Cao, Lujia Pan, Yuan YAO

One of the reasons is that the learned representations (i. e. features) from the imbalanced datasets are less effective than those from balanced datasets.

Capacity Analysis of Holographic MIMO Channels with Practical Constraints

no code implementations29 Dec 2022 Yuan Zhang, Jianhua Zhang, Yuxiang Zhang, Yuan YAO, Guangyi Liu

However, the channel might not satisfy isotropic scattering because of generalized angle distributions, and the antenna gain is limited by the array aperture in reality.

Exploring Vision Transformers as Diffusion Learners

no code implementations28 Dec 2022 He Cao, Jianan Wang, Tianhe Ren, Xianbiao Qi, Yihao Chen, Yuan YAO, Lei Zhang

We further provide a hypothesis on the implication of disentangling the generative backbone as an encoder-decoder structure and show proof-of-concept experiments verifying the effectiveness of a stronger encoder for generative tasks with ASymmetriC ENcoder Decoder (ASCEND).

Beyond Object Recognition: A New Benchmark towards Object Concept Learning

no code implementations ICCV 2023 Yong-Lu Li, Yue Xu, Xinyu Xu, Xiaohan Mao, Yuan YAO, SiQi Liu, Cewu Lu

To support OCL, we build a densely annotated knowledge base including extensive labels for three levels of object concept (category, attribute, affordance), and the causal relations of three levels.

Attribute Object +1

Visually Grounded Commonsense Knowledge Acquisition

1 code implementation22 Nov 2022 Yuan YAO, Tianyu Yu, Ao Zhang, Mengdi Li, Ruobing Xie, Cornelius Weber, Zhiyuan Liu, Hai-Tao Zheng, Stefan Wermter, Tat-Seng Chua, Maosong Sun

In this work, we present CLEVER, which formulates CKE as a distantly supervised multi-instance learning problem, where models learn to summarize commonsense relations from a bag of images about an entity pair without any human annotation on image instances.

Language Modelling

StrokeGAN+: Few-Shot Semi-Supervised Chinese Font Generation with Stroke Encoding

no code implementations11 Nov 2022 Jinshan Zeng, Yefei Wang, Qi Chen, Yunxin Liu, Mingwen Wang, Yuan YAO

The effectiveness of the proposed model for the zero-shot traditional Chinese font generation is also evaluated in this paper.

Font Generation

An Embarrassingly Simple Backdoor Attack on Self-supervised Learning

3 code implementations ICCV 2023 Changjiang Li, Ren Pang, Zhaohan Xi, Tianyu Du, Shouling Ji, Yuan YAO, Ting Wang

As a new paradigm in machine learning, self-supervised learning (SSL) is capable of learning high-quality representations of complex data without relying on labels.

Adversarial Robustness Backdoor Attack +2

A Max-relevance-min-divergence Criterion for Data Discretization with Applications on Naive Bayes

no code implementations20 Sep 2022 Shihe Wang, Jianfeng Ren, Ruibin Bai, Yuan YAO, Xudong Jiang

Thus, we propose a Max-Dependency-Min-Divergence (MDmD) criterion that maximizes both the discriminant information and generalization ability of the discretized data.

Attribute Classification

Confidence Matters: Inspecting Backdoors in Deep Neural Networks via Distribution Transfer

no code implementations13 Aug 2022 Tong Wang, Yuan YAO, Feng Xu, Miao Xu, Shengwei An, Ting Wang

Existing defenses are mainly built upon the observation that the backdoor trigger is usually of small size or affects the activation of only a few neurons.

Backdoor Attack backdoor defense

DCT-Net: Domain-Calibrated Translation for Portrait Stylization

3 code implementations6 Jul 2022 Yifang Men, Yuan YAO, Miaomiao Cui, Zhouhui Lian, Xuansong Xie

This paper introduces DCT-Net, a novel image translation architecture for few-shot portrait stylization.

Few-Shot Learning Style Transfer +1

Unsupervised Domain Adaptation through Shape Modeling for Medical Image Segmentation

1 code implementation6 Jul 2022 Yuan YAO, Fengze Liu, Zongwei Zhou, Yan Wang, Wei Shen, Alan Yuille, Yongyi Lu

Previous methods proposed Variational Autoencoder (VAE) based models to learn the distribution of shape for a particular organ and used it to automatically evaluate the quality of a segmentation prediction by fitting it into the learned shape distribution.

Image Segmentation Pancreas Segmentation +3

On Private Online Convex Optimization: Optimal Algorithms in $\ell_p$-Geometry and High Dimensional Contextual Bandits

1 code implementation16 Jun 2022 Yuxuan Han, Zhicong Liang, Zhipeng Liang, Yang Wang, Yuan YAO, Jiheng Zhang

To address such a challenge as the online convex optimization with privacy protection, we propose a private variant of online Frank-Wolfe algorithm with recursive gradients for variance reduction to update and reveal the parameters upon each data.

Multi-Armed Bandits

Prompt Tuning for Discriminative Pre-trained Language Models

1 code implementation Findings (ACL) 2022 Yuan YAO, Bowen Dong, Ao Zhang, Zhengyan Zhang, Ruobing Xie, Zhiyuan Liu, Leyu Lin, Maosong Sun, Jianyong Wang

Recent works have shown promising results of prompt tuning in stimulating pre-trained language models (PLMs) for natural language processing (NLP) tasks.

Language Modelling Question Answering +2

PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models

1 code implementation23 May 2022 Yuan YAO, Qianyu Chen, Ao Zhang, Wei Ji, Zhiyuan Liu, Tat-Seng Chua, Maosong Sun

We show that PEVL enables state-of-the-art performance of detector-free VLP models on position-sensitive tasks such as referring expression comprehension and phrase grounding, and also improves the performance on position-insensitive tasks with grounded inputs.

Language Modelling Object +7

Detecting Topology Attacks against Graph Neural Networks

no code implementations21 Apr 2022 Senrong Xu, Yuan YAO, Liangyue Li, Wei Yang, Feng Xu, Hanghang Tong

In this work, we study the victim node detection problem under topology attacks against GNNs.

Node Classification

NeuroMixGDP: A Neural Collapse-Inspired Random Mixup for Private Data Release

1 code implementation14 Feb 2022 Donghao Li, Yang Cao, Yuan YAO

To further enhance the utility and address the label collapse issue when the mixup degree is large, we propose a Hierarchical sampling method to stratify the mixup samples on a small number of classes.

Data Augmentation Privacy Preserving +1

Unpaired Cartoon Image Synthesis via Gated Cycle Mapping

no code implementations CVPR 2022 Yifang Men, Yuan YAO, Miaomiao Cui, Zhouhui Lian, Xuansong Xie, Xian-Sheng Hua

Experimental results demonstrate the superiority of the proposed method over the state of the art and validate its effectiveness in the brand-new task of general cartoon image synthesis.

Image Generation Video Generation

Backdoor Attack through Frequency Domain

1 code implementation22 Nov 2021 Tong Wang, Yuan YAO, Feng Xu, Shengwei An, Hanghang Tong, Ting Wang

We also evaluate FTROJAN against state-of-the-art defenses as well as several adaptive defenses that are designed on the frequency domain.

Autonomous Driving Backdoor Attack

Federated Deep Learning with Bayesian Privacy

no code implementations27 Sep 2021 Hanlin Gu, Lixin Fan, Bowen Li, Yan Kang, Yuan YAO, Qiang Yang

To address the aforementioned perplexity, we propose a novel Bayesian Privacy (BP) framework which enables Bayesian restoration attacks to be formulated as the probability of reconstructing private data from observed public information.

Federated Learning Image Classification +1

CPT: Colorful Prompt Tuning for Pre-trained Vision-Language Models

1 code implementation24 Sep 2021 Yuan YAO, Ao Zhang, Zhengyan Zhang, Zhiyuan Liu, Tat-Seng Chua, Maosong Sun

Pre-Trained Vision-Language Models (VL-PTMs) have shown promising capabilities in grounding natural language in image data, facilitating a broad variety of cross-modal tasks.

Visual Grounding

A Note on Learning Rare Events in Molecular Dynamics using LSTM and Transformer

1 code implementation14 Jul 2021 Wenqi Zeng, Siqin Cao, Xuhui Huang, Yuan YAO

Therefore, to learn rare events of slow molecular dynamics by LSTM and Transformer, it is critical to choose proper temporal resolution (i. e., saving intervals of MD simulation trajectories) and state partition in high resolution data, since deep neural network models might not automatically disentangle slow dynamics from fast dynamics when both are present in data influencing each other.

Language Modelling

CPM-2: Large-scale Cost-effective Pre-trained Language Models

2 code implementations20 Jun 2021 Zhengyan Zhang, Yuxian Gu, Xu Han, Shengqi Chen, Chaojun Xiao, Zhenbo Sun, Yuan YAO, Fanchao Qi, Jian Guan, Pei Ke, Yanzheng Cai, Guoyang Zeng, Zhixing Tan, Zhiyuan Liu, Minlie Huang, Wentao Han, Yang Liu, Xiaoyan Zhu, Maosong Sun

We present a suite of cost-effective techniques for the use of PLMs to deal with the efficiency issues of pre-training, fine-tuning, and inference.

Turn the Combination Lock: Learnable Textual Backdoor Attacks via Word Substitution

1 code implementation ACL 2021 Fanchao Qi, Yuan YAO, Sophia Xu, Zhiyuan Liu, Maosong Sun

Recent studies show that neural natural language processing (NLP) models are vulnerable to backdoor attacks.

Open Hierarchical Relation Extraction

1 code implementation NAACL 2021 Kai Zhang, Yuan YAO, Ruobing Xie, Xu Han, Zhiyuan Liu, Fen Lin, Leyu Lin, Maosong Sun

To establish the bidirectional connections between OpenRE and relation hierarchy, we propose the task of open hierarchical relation extraction and present a novel OHRE framework for the task.

Clustering Relation +1

Image-to-Video Generation via 3D Facial Dynamics

no code implementations31 May 2021 Xiaoguang Tu, Yingtian Zou, Jian Zhao, Wenjie Ai, Jian Dong, Yuan YAO, Zhikang Wang, Guodong Guo, Zhifeng Li, Wei Liu, Jiashi Feng

Video generation from a single face image is an interesting problem and usually tackled by utilizing Generative Adversarial Networks (GANs) to integrate information from the input face image and a sequence of sparse facial landmarks.

Image to Video Generation Video Prediction

Visual Distant Supervision for Scene Graph Generation

1 code implementation ICCV 2021 Yuan YAO, Ao Zhang, Xu Han, Mengdi Li, Cornelius Weber, Zhiyuan Liu, Stefan Wermter, Maosong Sun

In this work, we propose visual distant supervision, a novel paradigm of visual relation learning, which can train scene graph models without any human-labeled data.

Graph Generation Predicate Classification +2

UPRec: User-Aware Pre-training for Recommender Systems

no code implementations22 Feb 2021 Chaojun Xiao, Ruobing Xie, Yuan YAO, Zhiyuan Liu, Maosong Sun, Xu Zhang, Leyu Lin

Existing sequential recommendation methods rely on large amounts of training data and usually suffer from the data sparsity problem.

Self-Supervised Learning Sequential Recommendation

Polyimide-Based Flexible Coupled-Coils Design and Load-Shift Keying Analysis

no code implementations2 Feb 2021 Yuan YAO, Wing-Hung Ki, Chi-Ying Tsui

A thorough analysis is done for the ideal and practical scenario and it shows that a mismatched secondary LC tank will affect the communication range and communication correctness.

On Stochastic Variance Reduced Gradient Method for Semidefinite Optimization

no code implementations1 Jan 2021 Jinshan Zeng, Yixuan Zha, Ke Ma, Yuan YAO

In this paper, we fill this gap via exploiting a new semi-stochastic variant of the original SVRG with Option I adapted to the semidefinite optimization.

Computational Efficiency

StrokeGAN: Reducing Mode Collapse in Chinese Font Generation via Stroke Encoding

1 code implementation16 Dec 2020 Jinshan Zeng, Qi Chen, Yunxin Liu, Mingwen Wang, Yuan YAO

However, these deep generative models may suffer from the mode collapse issue, which significantly degrades the diversity and quality of generated results.

Font Generation

An exact solution in Markov decision process with multiplicative rewards as a general framework

no code implementations15 Dec 2020 Yuan YAO, Xiaolin Sun

We first review the exact solution of conventional linear quadratic regulation with a linear transition and a Gaussian noise, whose optimal policy does not depend on the Gaussian noise, which is an undesired feature in the presence of significant noises.

Parafermionization, bosonization, and critical parafermionic theories

no code implementations14 Dec 2020 Yuan YAO, Akira Furusaki

We formulate a $\mathbb{Z}_k$-parafermionization/bosonization scheme for one-dimensional lattice models and field theories on a torus, starting from a generalized Jordan-Wigner transformation on a lattice, which extends the Majorana-Ising duality at $k=2$.

Strongly Correlated Electrons Statistical Mechanics High Energy Physics - Theory Mathematical Physics Mathematical Physics

Denoising Relation Extraction from Document-level Distant Supervision

1 code implementation EMNLP 2020 Chaojun Xiao, Yuan YAO, Ruobing Xie, Xu Han, Zhiyuan Liu, Maosong Sun, Fen Lin, Leyu Lin

Distant supervision (DS) has been widely used to generate auto-labeled data for sentence-level relation extraction (RE), which improves RE performance.

Denoising Document-level Relation Extraction +2

Adversarial Robustness of Stabilized NeuralODEs Might be from Obfuscated Gradients

1 code implementation28 Sep 2020 Yifei Huang, Yaodong Yu, Hongyang Zhang, Yi Ma, Yuan YAO

Even replacing only the first layer of a ResNet by such a ODE block can exhibit further improvement in robustness, e. g., under PGD-20 ($\ell_\infty=0. 031$) attack on CIFAR-10 dataset, it achieves 91. 57\% and natural accuracy and 62. 35\% robust accuracy, while a counterpart architecture of ResNet trained with TRADES achieves natural and robust accuracy 76. 29\% and 45. 24\%, respectively.

Adversarial Defense Adversarial Robustness

Knowledge Transfer via Pre-training for Recommendation: A Review and Prospect

no code implementations19 Sep 2020 Zheni Zeng, Chaojun Xiao, Yuan YAO, Ruobing Xie, Zhiyuan Liu, Fen Lin, Leyu Lin, Maosong Sun

Recommender systems aim to provide item recommendations for users, and are usually faced with data sparsity problem (e. g., cold start) in real-world scenarios.

Recommendation Systems Transfer Learning

Generative Adversarial Networks for Robust Cryo-EM Image Denoising

1 code implementation17 Aug 2020 Hanlin Gu, Yin Xian, Ilona Christy Unarta, Yuan YAO

Equipped with robust $\ell_1$ Autoencoder and some designs of robust $\beta$-GANs, one can stabilize the training of GANs and achieve the state-of-the-art performance of robust denoising with low SNR data and against possible information contamination.

3D Reconstruction Clustering +2

Multi-source Heterogeneous Domain Adaptation with Conditional Weighting Adversarial Network

1 code implementation6 Aug 2020 Yuan Yao, Xutao Li, Yu Zhang, Yunming Ye

In reality, however, it is not uncommon to obtain samples from multiple heterogeneous domains.

Domain Adaptation

Leveraging both Lesion Features and Procedural Bias in Neuroimaging: An Dual-Task Split dynamics of inverse scale space

no code implementations17 Jul 2020 Xinwei Sun, Wenjing Han, Lingjing Hu, Yuan YAO, Yizhou Wang

Specifically, with a variable the splitting term, two estimators are introduced and split apart, i. e. one is for feature selection (the sparse estimator) and the other is for prediction (the dense estimator).

feature selection

How to trust unlabeled data? Instance Credibility Inference for Few-Shot Learning

2 code implementations15 Jul 2020 Yikai Wang, Li Zhang, Yuan YAO, Yanwei Fu

We rank the credibility of pseudo-labeled instances along the regularization path of their corresponding incidental parameters, and the most trustworthy pseudo-labeled examples are preserved as the augmented labeled instances.

Data Augmentation Few-Shot Learning

DessiLBI: Exploring Structural Sparsity of Deep Networks via Differential Inclusion Paths

1 code implementation4 Jul 2020 Yanwei Fu, Chen Liu, Donghao Li, Xinwei Sun, Jinshan Zeng, Yuan YAO

Over-parameterization is ubiquitous nowadays in training neural networks to benefit both optimization in seeking global optima and generalization in reducing prediction error.

Crossmodal Language Grounding in an Embodied Neurocognitive Model

1 code implementation24 Jun 2020 Stefan Heinrich, Yuan YAO, Tobias Hinz, Zhiyuan Liu, Thomas Hummel, Matthias Kerzel, Cornelius Weber, Stefan Wermter

From a neuroscientific perspective, natural language is embodied, grounded in most, if not all, sensory and sensorimotor modalities, and acquired by means of crossmodal integration.

Video Playback Rate Perception for Self-supervisedSpatio-Temporal Representation Learning

1 code implementation20 Jun 2020 Yuan Yao, Chang Liu, Dezhao Luo, Yu Zhou, Qixiang Ye

The generative perception model acts as a feature decoder to focus on comprehending high temporal resolution and short-term representation by introducing a motion-attention mechanism.

Action Recognition Representation Learning +2

Video Playback Rate Perception for Self-Supervised Spatio-Temporal Representation Learning

1 code implementation CVPR 2020 Yuan Yao, Chang Liu, Dezhao Luo, Yu Zhou, Qixiang Ye

The generative perception model acts as a feature decoder to focus on comprehending high temporal resolution and short-term representation by introducing a motion-attention mechanism.

Representation Learning Retrieval +3

Differentially Private Federated Learning with Laplacian Smoothing

no code implementations1 May 2020 Zhicong Liang, Bao Wang, Quanquan Gu, Stanley Osher, Yuan YAO

Federated learning aims to protect data privacy by collaboratively learning a model without sharing private data among users.

Federated Learning

Boosting Semantic Human Matting with Coarse Annotations

1 code implementation CVPR 2020 Jinlin Liu, Yuan YAO, Wendi Hou, Miaomiao Cui, Xuansong Xie, Chang-Shui Zhang, Xian-Sheng Hua

In this paper, we propose to use coarse annotated data coupled with fine annotated data to boost end-to-end semantic human matting without trimaps as extra input.

Image Matting Semantic Segmentation

Learning the mapping $\mathbf{x}\mapsto \sum_{i=1}^d x_i^2$: the cost of finding the needle in a haystack

no code implementations24 Feb 2020 Jiefu Zhang, Leonardo Zepeda-Núñez, Yuan YAO, Lin Lin

When such structural information is not available, and we may only use a dense neural network, the optimization procedure to find the sparse network embedded in the dense network is similar to finding the needle in a haystack, using a given number of samples of the function.

Front2Back: Single View 3D Shape Reconstruction via Front to Back Prediction

1 code implementation CVPR 2020 Yuan Yao, Nico Schertler, Enrique Rosales, Helge Rhodin, Leonid Sigal, Alla Sheffer

Reconstruction of a 3D shape from a single 2D image is a classical computer vision problem, whose difficulty stems from the inherent ambiguity of recovering occluded or only partially observed surfaces.

3D Shape Reconstruction Surface Reconstruction

SMAUG: End-to-End Full-Stack Simulation Infrastructure for Deep Learning Workloads

no code implementations10 Dec 2019 Sam Likun Xi, Yuan YAO, Kshitij Bhardwaj, Paul Whatmough, Gu-Yeon Wei, David Brooks

In recent years, there has been tremendous advances in hardware acceleration of deep neural networks.

Fast Stochastic Ordinal Embedding with Variance Reduction and Adaptive Step Size

no code implementations1 Dec 2019 Ke Ma, Jinshan Zeng, Qianqian Xu, Xiaochun Cao, Wei Liu, Yuan YAO

Learning representation from relative similarity comparisons, often called ordinal embedding, gains rising attention in recent years.

Adversarial Language Games for Advanced Natural Language Intelligence

no code implementations5 Nov 2019 Yuan Yao, Haoxi Zhong, Zhengyan Zhang, Xu Han, Xiaozhi Wang, Chaojun Xiao, Guoyang Zeng, Zhiyuan Liu, Maosong Sun

In this work, we propose a challenging adversarial language game called Adversarial Taboo as an example, in which an attacker and a defender compete around a target word.

Board Games

iSplit LBI: Individualized Partial Ranking with Ties via Split LBI

1 code implementation NeurIPS 2019 Qianqian Xu, Xinwei Sun, Zhiyong Yang, Xiaochun Cao, Qingming Huang, Yuan YAO

In this paper, instead of learning a global ranking which is agreed with the consensus, we pursue the tie-aware partial ranking from an individualized perspective.

Characterizing Membership Privacy in Stochastic Gradient Langevin Dynamics

no code implementations5 Oct 2019 Bingzhe Wu, Chaochao Chen, Shiwan Zhao, Cen Chen, Yuan YAO, Guangyu Sun, Li Wang, Xiaolu Zhang, Jun Zhou

Based on this framework, we demonstrate that SGLD can prevent the information leakage of the training dataset to a certain extent.

Generalization Bounds

OpenNRE: An Open and Extensible Toolkit for Neural Relation Extraction

1 code implementation IJCNLP 2019 Xu Han, Tianyu Gao, Yuan YAO, Demin Ye, Zhiyuan Liu, Maosong Sun

OpenNRE is an open-source and extensible toolkit that provides a unified framework to implement neural models for relation extraction (RE).

Information Retrieval Question Answering +3

Boosting Network: Learn by Growing Filters and Layers via SplitLBI

no code implementations25 Sep 2019 Zuyuan Zhong, Chen Liu, Yanwei Fu, Yuan YAO

Network structures are important to learning good representations of many tasks in computer vision and machine learning communities.

Neural Architecture Search

Split LBI for Deep Learning: Structural Sparsity via Differential Inclusion Paths

no code implementations25 Sep 2019 Yanwei Fu, Chen Liu, Donghao Li, Xinwei Sun, Jinshan Zeng, Yuan YAO

Over-parameterization is ubiquitous nowadays in training neural networks to benefit both optimization in seeking global optima and generalization in reducing prediction error.

An Acceleration Framework for High Resolution Image Synthesis

no code implementations9 Sep 2019 Jinlin Liu, Yuan YAO, Jianqiang Ren

The proposed acceleration framework makes it possible to generate high resolution images using less training time with limited hardware resource.

Code Generation Image Generation +1

Heterogeneous Domain Adaptation via Soft Transfer Network

no code implementations28 Aug 2019 Yuan Yao, Yu Zhang, Xutao Li, Yunming Ye

Heterogeneous domain adaptation (HDA) aims to facilitate the learning task in a target domain by borrowing knowledge from a heterogeneous source domain.

Domain Adaptation

DocRED: A Large-Scale Document-Level Relation Extraction Dataset

4 code implementations ACL 2019 Yuan Yao, Deming Ye, Peng Li, Xu Han, Yankai Lin, Zheng-Hao Liu, Zhiyuan Liu, Lixin Huang, Jie zhou, Maosong Sun

Multiple entities in a document generally exhibit complex inter-sentence relations, and cannot be well handled by existing relation extraction (RE) methods that typically focus on extracting intra-sentence relations for single entity pairs.

Document-level Relation Extraction Relation +1

Exploring Structural Sparsity of Deep Networks via Inverse Scale Spaces

1 code implementation23 May 2019 Yanwei Fu, Chen Liu, Donghao Li, Zuyuan Zhong, Xinwei Sun, Jinshan Zeng, Yuan YAO

To fill in this gap, this paper proposes a new approach based on differential inclusions of inverse scale spaces, which generate a family of models from simple to complex ones along the dynamics via coupling a pair of parameters, such that over-parameterized deep models and their structural sparsity can be explored simultaneously.

ROBUST ESTIMATION VIA GENERATIVE ADVERSARIAL NETWORKS

no code implementations ICLR 2019 Chao GAO, jiyi LIU, Yuan YAO, Weizhi Zhu

In particular, we show that a JS-GAN that uses a neural network discriminator with at least one hidden layer is able to achieve the minimax rate of robust mean estimation under Huber's $\epsilon$-contamination model.

ON BREIMAN’S DILEMMA IN NEURAL NETWORKS: SUCCESS AND FAILURE OF NORMALIZED MARGINS

no code implementations ICLR 2019 Yifei HUANG, Yuan YAO, Weizhi Zhu

A belief persists long in machine learning that enlargement of margins over training data accounts for the resistance of models to overfitting by increasing the robustness.

Generalization Bounds

$S^{2}$-LBI: Stochastic Split Linearized Bregman Iterations for Parsimonious Deep Learning

no code implementations24 Apr 2019 Yanwei Fu, Donghao Li, Xinwei Sun, Shun Zhang, Yizhou Wang, Yuan YAO

This paper proposes a novel Stochastic Split Linearized Bregman Iteration ($S^{2}$-LBI) algorithm to efficiently train the deep network.

Computational Efficiency Model Selection

Deep Robust Subjective Visual Property Prediction in Crowdsourcing

no code implementations CVPR 2019 Qianqian Xu, Zhiyong Yang, Yangbangyan Jiang, Xiaochun Cao, Qingming Huang, Yuan YAO

The problem of estimating subjective visual properties (SVP) of images (e. g., Shoes A is more comfortable than B) is gaining rising attention.

Property Prediction

Generative Adversarial Nets for Robust Scatter Estimation: A Proper Scoring Rule Perspective

1 code implementation5 Mar 2019 Chao Gao, Yuan YAO, Weizhi Zhu

Robust scatter estimation is a fundamental task in statistics.

BOLT-SSI: A Statistical Approach to Screening Interaction Effects for Ultra-High Dimensional Data

1 code implementation10 Feb 2019 Min Zhou, Mingwei Dai, Yuan YAO, Jin Liu, Can Yang, Heng Peng

In this paper, we first propose a simple method for sure screening interactions (SSI).

Methodology

On ADMM in Deep Learning: Convergence and Saturation-Avoidance

1 code implementation6 Feb 2019 Jinshan Zeng, Shao-Bo Lin, Yuan YAO, Ding-Xuan Zhou

In this paper, we develop an alternating direction method of multipliers (ADMM) for deep neural networks training with sigmoid-type activation functions (called \textit{sigmoid-ADMM pair}), mainly motivated by the gradient-free nature of ADMM in avoiding the saturation of sigmoid-type activations and the advantages of deep neural networks with sigmoid-type activations (called deep sigmoid nets) over their rectified linear unit (ReLU) counterparts (called deep ReLU nets) in terms of approximation.

Attention-aware Multi-stroke Style Transfer

1 code implementation CVPR 2019 Yuan Yao, Jianqiang Ren, Xuansong Xie, Weidong Liu, Yong-Jin Liu, Jun Wang

Neural style transfer has drawn considerable attention from both academic and industrial field.

Style Transfer

Multiview Cross-supervision for Semantic Segmentation

no code implementations4 Dec 2018 Yuan Yao, Hyun Soo Park

We hypothesize that it is possible to leverage multiview image streams that are linked through the underlying 3D geometry, which can provide an additional supervisionary signal to train a segmentation model.

3D Reconstruction Camera Calibration +2

Data-Driven Tight Frame for Cryo-EM Image Denoising and Conformational Classification

1 code implementation20 Oct 2018 Yin Xian, Hanlin Gu, Wei Wang, Xuhui Huang, Yuan YAO, Yang Wang, Jian-Feng Cai

We introduce the use of data-driven tight frame (DDTF) algorithm for cryo-EM image denoising.

Computation Image and Video Processing

Rethinking Breiman's Dilemma in Neural Networks: Phase Transitions of Margin Dynamics

1 code implementation8 Oct 2018 Weizhi Zhu, Yifei HUANG, Yuan YAO

In this paper, we revisit Breiman's dilemma in deep neural networks with recently proposed spectrally normalized margins, from a novel perspective based on phase transitions of normalized margin distributions in training dynamics.

Generalization Bounds

A Unified Dynamic Approach to Sparse Model Selection

no code implementations8 Oct 2018 Chendi Huang, Yuan YAO

Sparse model selection is ubiquitous from linear regression to graphical models where regularization paths, as a family of estimators upon the regularization parameter varying, are computed when the regularization parameter is unknown or decided data-adaptively.

Model Selection regression

Robust Estimation and Generative Adversarial Nets

2 code implementations4 Oct 2018 Chao Gao, jiyi LIU, Yuan YAO, Weizhi Zhu

Similar to the derivation of $f$-GANs, we show that these depth functions that lead to statistically optimal robust estimators can all be viewed as variational lower bounds of the total variation distance in the framework of $f$-Learning.

A Margin-based MLE for Crowdsourced Partial Ranking

no code implementations29 Jul 2018 Qianqian Xu, Jiechao Xiong, Xinwei Sun, Zhiyong Yang, Xiaochun Cao, Qingming Huang, Yuan YAO

A preference order or ranking aggregated from pairwise comparison data is commonly understood as a strict total order.

MSplit LBI: Realizing Feature Selection and Dense Estimation Simultaneously in Few-shot and Zero-shot Learning

no code implementations ICML 2018 Bo Zhao, Xinwei Sun, Yanwei Fu, Yuan YAO, Yizhou Wang

To solve this task, $L_{1}$ regularization is widely used for the pursuit of feature selection and avoiding overfitting, and yet the sparse estimation of features in $L_{1}$ regularization may cause the underfitting of training data.

feature selection Zero-Shot Learning

MONET: Multiview Semi-supervised Keypoint Detection via Epipolar Divergence

1 code implementation ICCV 2019 Yuan Yao, Yasamin Jafarian, Hyun Soo Park

While multiview geometry can be used to self-supervise the unlabeled data, integrating the geometry into learning a keypoint detector is challenging due to representation mismatch.

Data Augmentation Keypoint Detection

A Proximal Block Coordinate Descent Algorithm for Deep Neural Network Training

no code implementations24 Mar 2018 Tim Tsz-Kit Lau, Jinshan Zeng, Baoyuan Wu, Yuan Yao

Training deep neural networks (DNNs) efficiently is a challenge due to the associated highly nonconvex optimization.

From Social to Individuals: a Parsimonious Path of Multi-level Models for Crowdsourced Preference Aggregation

no code implementations8 Mar 2018 Qianqian Xu, Jiechao Xiong, Xiaochun Cao, Qingming Huang, Yuan YAO

In crowdsourced preference aggregation, it is often assumed that all the annotators are subject to a common preference or social utility function which generates their comparison behaviors in experiments.

Global Convergence of Block Coordinate Descent in Deep Learning

2 code implementations1 Mar 2018 Jinshan Zeng, Tim Tsz-Kit Lau, Shao-Bo Lin, Yuan YAO

Deep learning has aroused extensive attention due to its great empirical success.

Zero-shot Learning via Shared-Reconstruction-Graph Pursuit

no code implementations20 Nov 2017 Bo Zhao, Xinwei Sun, Yuan YAO, Yizhou Wang

With the learned SRG, each unseen class prototype (cluster center) in the image feature space can be synthesized by the linear combination of other class prototypes, so that testing instances can be classified based on the distance to these synthesized prototypes.

Clustering Generalized Zero-Shot Learning +1

Stochastic Non-convex Ordinal Embedding with Stabilized Barzilai-Borwein Step Size

1 code implementation17 Nov 2017 Ke Ma, Jinshan Zeng, Jiechao Xiong, Qianqian Xu, Xiaochun Cao, Wei Liu, Yuan YAO

Learning representation from relative similarity comparisons, often called ordinal embedding, gains rising attention in recent years.

HodgeRank with Information Maximization for Crowdsourced Pairwise Ranking Aggregation

no code implementations16 Nov 2017 Qianqian Xu, Jiechao Xiong, Xi Chen, Qingming Huang, Yuan YAO

Recently, crowdsourcing has emerged as an effective paradigm for human-powered large scale problem solving in various domains.

Accelerated Block Coordinate Proximal Gradients with Applications in High Dimensional Statistics

no code implementations15 Oct 2017 Tsz Kit Lau, Yuan YAO

Nonconvex optimization problems arise in different research fields and arouse lots of attention in signal processing, statistics and machine learning.

BIG-bench Machine Learning regression +1

Exploring Outliers in Crowdsourced Ranking for QoE

no code implementations18 Jul 2017 Qianqian Xu, Ming Yan, Chendi Huang, Jiechao Xiong, Qingming Huang, Yuan YAO

Outlier detection is a crucial part of robust evaluation for crowdsourceable assessment of Quality of Experience (QoE) and has attracted much attention in recent years.

Outlier Detection

Visual Attribute Transfer through Deep Image Analogy

5 code implementations2 May 2017 Jing Liao, Yuan YAO, Lu Yuan, Gang Hua, Sing Bing Kang

We propose a new technique for visual attribute transfer across images that may have very different appearance but have perceptually similar semantic structure.

Attribute

Split LBI: An Iterative Regularization Path with Structural Sparsity

no code implementations NeurIPS 2016 Chendi Huang, Xinwei Sun, Jiechao Xiong, Yuan YAO

An iterative regularization path with structural sparsity is proposed in this paper based on variable splitting and the Linearized Bregman Iteration, hence called \emph{Split LBI}.

Image Denoising Model Selection

Parsimonious Mixed-Effects HodgeRank for Crowdsourced Preference Aggregation

no code implementations12 Jul 2016 Qianqian Xu, Jiechao Xiong, Xiaochun Cao, Yuan YAO

In crowdsourced preference aggregation, it is often assumed that all the annotators are subject to a common preference or utility function which generates their comparison behaviors in experiments.

False Discovery Rate Control and Statistical Quality Assessment of Annotators in Crowdsourced Ranking

no code implementations19 May 2016 Qianqian Xu, Jiechao Xiong, Xiaochun Cao, Yuan YAO

With the rapid growth of crowdsourcing platforms it has become easy and relatively inexpensive to collect a dataset labeled by multiple annotators in a short time.

Position Sociology

Analysis of Crowdsourced Sampling Strategies for HodgeRank with Sparse Random Graphs

no code implementations28 Feb 2015 Braxton Osting, Jiechao Xiong, Qianqian Xu, Yuan YAO

In this setting, a pairwise comparison dataset is typically gathered via random sampling, either \emph{with} or \emph{without} replacement.

Informativeness

Robust Subjective Visual Property Prediction from Crowdsourced Pairwise Labels

no code implementations25 Jan 2015 Yanwei Fu, Timothy M. Hospedales, Tao Xiang, Jiechao Xiong, Shaogang Gong, Yizhou Wang, Yuan YAO

In this paper, we propose a more principled way to identify annotation outliers by formulating the subjective visual property prediction task as a unified robust learning to rank problem, tackling both the outlier detection and learning to rank jointly.

Attribute Learning-To-Rank +2

Evaluating Visual Properties via Robust HodgeRank

no code implementations15 Aug 2014 Qianqian Xu, Jiechao Xiong, Xiaochun Cao, Qingming Huang, Yuan YAO

In this paper we study the problem of how to estimate such visual properties from a ranking perspective with the help of the annotators from online crowdsourcing platforms.

Graph Sampling Outlier Detection

Geometric Tight Frame based Stylometry for Art Authentication of van Gogh Paintings

no code implementations2 Jul 2014 Haixia Liu, Raymond H. Chan, Yuan YAO

Then a forward stage-wise rank boosting is used to select a small set of features for more accurate classification so that van Gogh paintings are highly concentrated towards some center point while forgeries are spread out as outliers.

Classification General Classification +1

Sparse Recovery via Differential Inclusions

1 code implementation30 Jun 2014 Stanley Osher, Feng Ruan, Jiechao Xiong, Yuan YAO, Wotao Yin

In this paper, we recover sparse signals from their noisy linear measurements by solving nonlinear differential inclusions, which is based on the notion of inverse scale space (ISS) developed in applied mathematics.

Want a Good Answer? Ask a Good Question First!

no code implementations27 Nov 2013 Yuan Yao, Hanghang Tong, Tao Xie, Leman Akoglu, Feng Xu, Jian Lu

Community Question Answering (CQA) websites have become valuable repositories which host a massive volume of human knowledge.

Community Question Answering

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