Search Results for author: Fan Wu

Found 78 papers, 28 papers with code

DenseBody: Directly Regressing Dense 3D Human Pose and Shape From a Single Color Image

2 code implementations25 Mar 2019 Pengfei Yao, Zheng Fang, Fan Wu, Yao Feng, Jiwei Li

Recovering 3D human body shape and pose from 2D images is a challenging task due to high complexity and flexibility of human body, and relatively less 3D labeled data.

Factor Graph Neural Network

1 code implementation3 Jun 2019 Zhen Zhang, Fan Wu, Wee Sun Lee

Most of the successful deep neural network architectures are structured, often consisting of elements like convolutional neural networks and gated recurrent neural networks.

VIGC: Visual Instruction Generation and Correction

2 code implementations24 Aug 2023 Bin Wang, Fan Wu, Xiao Han, Jiahui Peng, Huaping Zhong, Pan Zhang, Xiaoyi Dong, Weijia Li, Wei Li, Jiaqi Wang, Conghui He

A practical solution to this problem would be to utilize the available multimodal large language models (MLLMs) to generate instruction data for vision-language tasks.

Hallucination Image Captioning +1

DataLens: Scalable Privacy Preserving Training via Gradient Compression and Aggregation

2 code implementations20 Mar 2021 Boxin Wang, Fan Wu, Yunhui Long, Luka Rimanic, Ce Zhang, Bo Li

In this paper, we aim to explore the power of generative models and gradient sparsity, and propose a scalable privacy-preserving generative model DATALENS.

Dimensionality Reduction Navigate +1

Scalability vs. Utility: Do We Have to Sacrifice One for the Other in Data Importance Quantification?

1 code implementation CVPR 2021 Ruoxi Jia, Fan Wu, Xuehui Sun, Jiacen Xu, David Dao, Bhavya Kailkhura, Ce Zhang, Bo Li, Dawn Song

Quantifying the importance of each training point to a learning task is a fundamental problem in machine learning and the estimated importance scores have been leveraged to guide a range of data workflows such as data summarization and domain adaption.

Data Summarization Domain Adaptation

Accurate Protein Structure Prediction by Embeddings and Deep Learning Representations

3 code implementations9 Nov 2019 Iddo Drori, Darshan Thaker, Arjun Srivatsa, Daniel Jeong, Yueqi Wang, Linyong Nan, Fan Wu, Dimitri Leggas, Jinhao Lei, Weiyi Lu, Weilong Fu, Yuan Gao, Sashank Karri, Anand Kannan, Antonio Moretti, Mohammed AlQuraishi, Chen Keasar, Itsik Pe'er

Our dataset consists of amino acid sequences, Q8 secondary structures, position specific scoring matrices, multiple sequence alignment co-evolutionary features, backbone atom distance matrices, torsion angles, and 3D coordinates.

Multiple Sequence Alignment Protein Structure Prediction

Normal Learning in Videos with Attention Prototype Network

1 code implementation25 Aug 2021 Chao Hu, Fan Wu, Weijie Wu, Weibin Qiu, Shengxin Lai

With models trained on the normal data, the reconstruction errors of anomalous scenes are usually much larger than those of normal ones.

Anomaly Detection Video Anomaly Detection

Secure Federated Submodel Learning

1 code implementation6 Nov 2019 Chaoyue Niu, Fan Wu, Shaojie Tang, Lifeng Hua, Rongfei Jia, Chengfei Lv, Zhihua Wu, Guihai Chen

Nevertheless, the "position" of a client's truly required submodel corresponds to her private data, and its disclosure to the cloud server during interactions inevitably breaks the tenet of federated learning.

Federated Learning Position

CROP: Certifying Robust Policies for Reinforcement Learning through Functional Smoothing

2 code implementations ICLR 2022 Fan Wu, Linyi Li, Zijian Huang, Yevgeniy Vorobeychik, Ding Zhao, Bo Li

We then develop a local smoothing algorithm for policies derived from Q-functions to guarantee the robustness of actions taken along the trajectory; we also develop a global smoothing algorithm for certifying the lower bound of a finite-horizon cumulative reward, as well as a novel local smoothing algorithm to perform adaptive search in order to obtain tighter reward certification.

Atari Games Autonomous Vehicles +2

COPA: Certifying Robust Policies for Offline Reinforcement Learning against Poisoning Attacks

1 code implementation ICLR 2022 Fan Wu, Linyi Li, Chejian Xu, huan zhang, Bhavya Kailkhura, Krishnaram Kenthapadi, Ding Zhao, Bo Li

We leverage COPA to certify three RL environments trained with different algorithms and conclude: (1) The proposed robust aggregation protocols such as temporal aggregation can significantly improve the certifications; (2) Our certification for both per-state action stability and cumulative reward bound are efficient and tight; (3) The certification for different training algorithms and environments are different, implying their intrinsic robustness properties.

Offline RL reinforcement-learning +1

Federated Submodel Optimization for Hot and Cold Data Features

1 code implementation16 Sep 2021 Yucheng Ding, Chaoyue Niu, Fan Wu, Shaojie Tang, Chengfei Lv, Yanghe Feng, Guihai Chen

We theoretically proved the convergence rate of FedSubAvg by deriving an upper bound under a new metric called the element-wise gradient norm.

Federated Learning

G-NAS: Generalizable Neural Architecture Search for Single Domain Generalization Object Detection

1 code implementation7 Feb 2024 Fan Wu, Jinling Gao, Lanqing Hong, Xinbing Wang, Chenghu Zhou, Nanyang Ye

To address this issue, we propose the Generalizable loss (G-loss), which is an OoD-aware objective, preventing NAS from over-fitting by using gradient descent to optimize parameters not only on a subset of easy-to-learn features but also the remaining predictive features for generalization, and the overall framework is named G-NAS.

Domain Generalization Neural Architecture Search +2

Distributed Non-Convex Optimization with Sublinear Speedup under Intermittent Client Availability

1 code implementation18 Feb 2020 Yikai Yan, Chaoyue Niu, Yucheng Ding, Zhenzhe Zheng, Fan Wu, Guihai Chen, Shaojie Tang, Zhihua Wu

In this work, we consider a practical and ubiquitous issue when deploying federated learning in mobile environments: intermittent client availability, where the set of eligible clients may change during the training process.

Benchmarking Federated Learning

SecretGen: Privacy Recovery on Pre-Trained Models via Distribution Discrimination

1 code implementation25 Jul 2022 Zhuowen Yuan, Fan Wu, Yunhui Long, Chaowei Xiao, Bo Li

We first explore different statistical information which can discriminate the private training distribution from other distributions.

Model Selection Transfer Learning

EBFT: Effective and Block-Wise Fine-Tuning for Sparse LLMs

1 code implementation19 Feb 2024 Song Guo, Fan Wu, Lei Zhang, Xiawu Zheng, Shengchuan Zhang, Fei Chao, Yiyu Shi, Rongrong Ji

For instance, on the Wikitext2 dataset with LlamaV1-7B at 70% sparsity, our proposed EBFT achieves a perplexity of 16. 88, surpassing the state-of-the-art DSnoT with a perplexity of 75. 14.

Online Pricing with Reserve Price Constraint for Personal Data Markets

1 code implementation28 Nov 2019 Chaoyue Niu, Zhenzhe Zheng, Fan Wu, Shaojie Tang, Guihai Chen

The analysis and evaluation results reveal that our proposed pricing mechanism incurs low practical regret, online latency, and memory overhead, and also demonstrate that the existence of reserve price can mitigate the cold-start problem in a posted price mechanism, and thus can reduce the cumulative regret.

Understanding the Impact of Adversarial Robustness on Accuracy Disparity

1 code implementation28 Nov 2022 Yuzheng Hu, Fan Wu, Hongyang Zhang, Han Zhao

More specifically, we demonstrate that while the constraint of adversarial robustness consistently degrades the standard accuracy in the balanced class setting, the class imbalance ratio plays a fundamentally different role in accuracy disparity compared to the Gaussian case, due to the heavy tail of the stable distribution.

Adversarial Robustness Open-Ended Question Answering

Visual Natural Language Query Auto-Completion for Estimating Instance Probabilities

1 code implementation10 Oct 2019 Samuel Sharpe, Jin Yan, Fan Wu, Iddo Drori

Given the complete query, we fine tune a BERT embedding for estimating probabilities of a broad set of instances.

Hadamard Wirtinger Flow for Sparse Phase Retrieval

2 code implementations1 Jun 2020 Fan Wu, Patrick Rebeschini

We consider the problem of reconstructing an $n$-dimensional $k$-sparse signal from a set of noiseless magnitude-only measurements.

Retrieval

Deep learning-based identification of sub-nuclear structures in FIB-SEM images

1 code implementation19 Jul 2022 Niraj Gupta, Eric J. Roberts, Song Pang, C. Shan Xu, Harald F. Hess, Fan Wu, Abby Dernburg, Danielle Jorgens, Petrus H. Zwart, Vignesh Kasinath

Lastly, we highlight specific aspects of the model that can be optimized for its broad application to other volumetric imaging data as well as in situ cryo-electron tomography.

Electron Tomography Morphological Analysis

An End-to-End Approach to Natural Language Object Retrieval via Context-Aware Deep Reinforcement Learning

no code implementations22 Mar 2017 Fan Wu, Zhongwen Xu, Yi Yang

We propose an end-to-end approach to the natural language object retrieval task, which localizes an object within an image according to a natural language description, i. e., referring expression.

Object Referring Expression +1

Global Semantic Consistency for Zero-Shot Learning

no code implementations22 Jun 2018 Fan Wu, Kai Tian, Jihong Guan, Shuigeng Zhou

In this paper, we propose an end-to-end framework, called Global Semantic Consistency Network (GSC-Net for short), which makes complete use of the semantic information of both seen and unseen classes, to support effective zero-shot learning.

Attribute Generalized Zero-Shot Learning +1

From Server-Based to Client-Based Machine Learning: A Comprehensive Survey

no code implementations18 Sep 2019 Renjie Gu, Chaoyue Niu, Fan Wu, Guihai Chen, Chun Hu, Chengfei Lyu, Zhihua Wu

Another benefit is the bandwidth reduction because various kinds of local data can be involved in the training process without being uploaded.

BIG-bench Machine Learning

DeGNN: Characterizing and Improving Graph Neural Networks with Graph Decomposition

no code implementations10 Oct 2019 Xupeng Miao, Nezihe Merve Gürel, Wentao Zhang, Zhichao Han, Bo Li, Wei Min, Xi Rao, Hansheng Ren, Yinan Shan, Yingxia Shao, Yujie Wang, Fan Wu, Hui Xue, Yaming Yang, Zitao Zhang, Yang Zhao, Shuai Zhang, Yujing Wang, Bin Cui, Ce Zhang

Despite the wide application of Graph Convolutional Network (GCN), one major limitation is that it does not benefit from the increasing depth and suffers from the oversmoothing problem.

A Deep Prediction Network for Understanding Advertiser Intent and Satisfaction

no code implementations20 Aug 2020 Liyi Guo, Rui Lu, Haoqi Zhang, Junqi Jin, Zhenzhe Zheng, Fan Wu, Jin Li, Haiyang Xu, Han Li, Wenkai Lu, Jian Xu, Kun Gai

For e-commerce platforms such as Taobao and Amazon, advertisers play an important role in the entire digital ecosystem: their behaviors explicitly influence users' browsing and shopping experience; more importantly, advertiser's expenditure on advertising constitutes a primary source of platform revenue.

Marketing

IEO: Intelligent Evolutionary Optimisation for Hyperparameter Tuning

no code implementations10 Sep 2020 Yuxi Huan, Fan Wu, Michail Basios, Leslie Kanthan, Lingbo Li, Baowen Xu

In this paper, we introduce an intelligent evolutionary optimisation algorithm which applies machine learning technique to the traditional evolutionary algorithm to accelerate the overall optimisation process of tuning machine learning models in classification problems.

BIG-bench Machine Learning

A Continuous-Time Mirror Descent Approach to Sparse Phase Retrieval

1 code implementation NeurIPS 2020 Fan Wu, Patrick Rebeschini

We analyze continuous-time mirror descent applied to sparse phase retrieval, which is the problem of recovering sparse signals from a set of magnitude-only measurements.

Retrieval

A Multi-Agent-Based Rolling Optimization Method for Restoration Scheduling of Electrical Distribution Systems with Distributed Generation

no code implementations29 Dec 2018 Donghan Feng, Fan Wu, Yun Zhou, Usama Rahman, Xiaojin Zhao, Chen Fang

A multi-agent-based rolling optimization method for EDS restoration scheduling is proposed in this paper.

Signal Processing

Empowering the Edge Intelligence by Air-Ground Integrated Federated Learning in 6G Networks

no code implementations26 Jul 2020 Yuben Qu, Chao Dong, Jianchao Zheng, Qihui Wu, Yun Shen, Fan Wu, Alagan Anpalagan

Ubiquitous intelligence has been widely recognized as a critical vision of the future sixth generation (6G) networks, which implies the intelligence over the whole network from the core to the edge including end devices.

Networking and Internet Architecture

Cryptocurrency Trading: A Comprehensive Survey

no code implementations25 Mar 2020 Fan Fang, Carmine Ventre, Michail Basios, Leslie Kanthan, Lingbo Li, David Martinez-Regoband, Fan Wu

This paper provides a comprehensive survey of cryptocurrency trading research, by covering 146 research papers on various aspects of cryptocurrency trading (e. g., cryptocurrency trading systems, bubble and extreme conditions, prediction of volatility and return, crypto-assets portfolio construction and crypto-assets, technical trading and others).

Management

Optimizing Multiple Performance Metrics with Deep GSP Auctions for E-commerce Advertising

no code implementations5 Dec 2020 Zhilin Zhang, Xiangyu Liu, Zhenzhe Zheng, Chenrui Zhang, Miao Xu, Junwei Pan, Chuan Yu, Fan Wu, Jian Xu, Kun Gai

In e-commerce advertising, the ad platform usually relies on auction mechanisms to optimize different performance metrics, such as user experience, advertiser utility, and platform revenue.

Toward Understanding the Influence of Individual Clients in Federated Learning

no code implementations20 Dec 2020 Yihao Xue, Chaoyue Niu, Zhenzhe Zheng, Shaojie Tang, Chengfei Lv, Fan Wu, Guihai Chen

Federated learning allows mobile clients to jointly train a global model without sending their private data to a central server.

Federated Learning

Direct Observation of Thermalization to a Rayleigh-Jeans Distribution in Multimode Optical Fibers

no code implementations22 Dec 2020 Hamed Pourbeyram, Pavel Sidorenko, Fan Wu, Logan Wright, Demetrios Christodoulides, Frank Wise

Recent years have witnessed a resurgence of interest in nonlinear multimode optical systems where a host of intriguing effects have been observed that are impossible in single-mode settings.

Optics

FamDroid: Learning-Based Android Malware Family Classification Using Static Analysis

no code implementations11 Jan 2021 Wenhao fan, Liang Zhao, Jiayang Wang, Ye Chen, Fan Wu, Yuan'an Liu

At present, the main problem of existing research works on Android malware family classification lies in that the extracted features are inadequate to represent the common behavior characteristics of the malware in malicious families, and leveraging a single classifier or a static ensemble classifier is restricted to further improve the accuracy of classification.

Malware Detection Cryptography and Security

Game-based Pricing and Task Offloading in Mobile Edge Computing Enabled Edge-Cloud Systems

no code implementations14 Jan 2021 Yi Su, Wenhao fan, Yuan'an Liu, Fan Wu

In this paper, we formulate a distributed mechanism to analyze the interaction between OSPs and IoT MDs in the MEC enabled edge-cloud system by appling multi-leader multi-follower two-tier Stackelberg game theory.

Edge-computing Computer Science and Game Theory

Decentralized Federated Learning for UAV Networks: Architecture, Challenges, and Opportunities

no code implementations15 Apr 2021 Yuben Qu, Haipeng Dai, Yan Zhuang, Jiafa Chen, Chao Dong, Fan Wu, Song Guo

Unmanned aerial vehicles (UAVs), or say drones, are envisioned to support extensive applications in next-generation wireless networks in both civil and military fields.

Federated Learning

Nearly Minimax-Optimal Rates for Noisy Sparse Phase Retrieval via Early-Stopped Mirror Descent

1 code implementation8 May 2021 Fan Wu, Patrick Rebeschini

This paper studies early-stopped mirror descent applied to noisy sparse phase retrieval, which is the problem of recovering a $k$-sparse signal $\mathbf{x}^\star\in\mathbb{R}^n$ from a set of quadratic Gaussian measurements corrupted by sub-exponential noise.

Retrieval

Implicit Regularization in Matrix Sensing via Mirror Descent

1 code implementation NeurIPS 2021 Fan Wu, Patrick Rebeschini

We study discrete-time mirror descent applied to the unregularized empirical risk in matrix sensing.

We Know What You Want: An Advertising Strategy Recommender System for Online Advertising

no code implementations25 May 2021 Liyi Guo, Junqi Jin, Haoqi Zhang, Zhenzhe Zheng, Zhiye Yang, Zhizhuang Xing, Fei Pan, Lvyin Niu, Fan Wu, Haiyang Xu, Chuan Yu, Yuning Jiang, Xiaoqiang Zhu

To achieve this goal, the advertising platform needs to identify the advertiser's optimization objectives, and then recommend the corresponding strategies to fulfill the objectives.

Recommendation Systems

Neural Auction: End-to-End Learning of Auction Mechanisms for E-Commerce Advertising

no code implementations7 Jun 2021 Xiangyu Liu, Chuan Yu, Zhilin Zhang, Zhenzhe Zheng, Yu Rong, Hongtao Lv, Da Huo, YiQing Wang, Dagui Chen, Jian Xu, Fan Wu, Guihai Chen, Xiaoqiang Zhu

In e-commerce advertising, it is crucial to jointly consider various performance metrics, e. g., user experience, advertiser utility, and platform revenue.

Ready for Emerging Threats to Recommender Systems? A Graph Convolution-based Generative Shilling Attack

no code implementations22 Jul 2021 Fan Wu, Min Gao, Junliang Yu, Zongwei Wang, Kecheng Liu, Xu Wange

To explore the robustness of recommender systems, researchers have proposed various shilling attack models and analyzed their adverse effects.

Generative Adversarial Network Recommendation Systems

LinkTeller: Recovering Private Edges from Graph Neural Networks via Influence Analysis

no code implementations14 Aug 2021 Fan Wu, Yunhui Long, Ce Zhang, Bo Li

We show that these DP GCN mechanisms are not always resilient against LinkTeller empirically under mild privacy guarantees ($\varepsilon>5$).

Privacy Preserving Recommendation Systems +1

Data-Free Evaluation of User Contributions in Federated Learning

no code implementations24 Aug 2021 Hongtao Lv, Zhenzhe Zheng, Tie Luo, Fan Wu, Shaojie Tang, Lifeng Hua, Rongfei Jia, Chengfei Lv

We evaluate the performance of PCA and Fed-PCA using the MNIST dataset and a large industrial product recommendation dataset.

Federated Learning Product Recommendation

On-Device Learning with Cloud-Coordinated Data Augmentation for Extreme Model Personalization in Recommender Systems

no code implementations24 Jan 2022 Renjie Gu, Chaoyue Niu, Yikai Yan, Fan Wu, Shaojie Tang, Rongfeng Jia, Chengfei Lyu, Guihai Chen

Data heterogeneity is an intrinsic property of recommender systems, making models trained over the global data on the cloud, which is the mainstream in industry, non-optimal to each individual user's local data distribution.

Data Augmentation Recommendation Systems

Vertical Federated Learning: Challenges, Methodologies and Experiments

no code implementations9 Feb 2022 Kang Wei, Jun Li, Chuan Ma, Ming Ding, Sha Wei, Fan Wu, Guihai Chen, Thilina Ranbaduge

As a special architecture in FL, vertical FL (VFL) is capable of constructing a hyper ML model by embracing sub-models from different clients.

Vertical Federated Learning

Walle: An End-to-End, General-Purpose, and Large-Scale Production System for Device-Cloud Collaborative Machine Learning

no code implementations30 May 2022 Chengfei Lv, Chaoyue Niu, Renjie Gu, Xiaotang Jiang, Zhaode Wang, Bin Liu, Ziqi Wu, Qiulin Yao, Congyu Huang, Panos Huang, Tao Huang, Hui Shu, Jinde Song, Bin Zou, Peng Lan, Guohuan Xu, Fei Wu, Shaojie Tang, Fan Wu, Guihai Chen

Walle consists of a deployment platform, distributing ML tasks to billion-scale devices in time; a data pipeline, efficiently preparing task input; and a compute container, providing a cross-platform and high-performance execution environment, while facilitating daily task iteration.

To Store or Not? Online Data Selection for Federated Learning with Limited Storage

no code implementations1 Sep 2022 Chen Gong, Zhenzhe Zheng, Yunfeng Shao, Bingshuai Li, Fan Wu, Guihai Chen

We first define a new data valuation metric for data evaluation and selection in FL with theoretical guarantees for speeding up model convergence and enhancing final model accuracy, simultaneously.

Data Valuation Federated Learning +4

ARSC-Net: Adventitious Respiratory Sound Classification Network Using Parallel Paths with Channel-Spatial Attention

no code implementations IEEE International Conference on Bioinformatics and Biomedicine 2022 Lei Xu, Jianhong Cheng, Jin Liu, Hulin Kuang, Fan Wu, Jianxin Wang

The two types of features are entered into the parallel encoders paths with residual attention for extracting feature representation, and then fused into a channel-spatial attention module to adaptively focus on the important features between channel and spatial part for the classification task.

Ranked #9 on Audio Classification on ICBHI Respiratory Sound Database (using extra training data)

Audio Classification Sound Classification

Mining Causality from Continuous-time Dynamics Models: An Application to Tsunami Forecasting

no code implementations10 Oct 2022 Fan Wu, Sanghyun Hong, Donsub Rim, Noseong Park, Kookjin Lee

However, parameterization of dynamics using a neural network makes it difficult for humans to identify causal structures in the data.

Time Series Time Series Analysis

On-Device Model Fine-Tuning with Label Correction in Recommender Systems

no code implementations21 Oct 2022 Yucheng Ding, Chaoyue Niu, Fan Wu, Shaojie Tang, Chengfei Lyu, Guihai Chen

To meet the practical requirements of low latency, low cost, and good privacy in online intelligent services, more and more deep learning models are offloaded from the cloud to mobile devices.

Click-Through Rate Prediction Recommendation Systems

One-Time Model Adaptation to Heterogeneous Clients: An Intra-Client and Inter-Image Attention Design

no code implementations11 Nov 2022 Yikai Yan, Chaoyue Niu, Fan Wu, Qinya Li, Shaojie Tang, Chengfei Lyu, Guihai Chen

The mainstream workflow of image recognition applications is first training one global model on the cloud for a wide range of classes and then serving numerous clients, each with heterogeneous images from a small subset of classes to be recognized.

Detection of brain activations induced by naturalistic stimuli in a pseudo model-driven way

no code implementations3 Dec 2022 Jiangcong Liu, Hao Ma, Yun Guan, Fan Wu, Le Xu, Yang Zhang, Lixia Tian

We evaluated the effectiveness of AINS with both statistical and predictive analyses on individual differences in sex and intelligence quotient (IQ), based on the four movie fMRI runs included in the Human Connectome Project dataset.

evoML Yellow Paper: Evolutionary AI and Optimisation Studio

no code implementations20 Dec 2022 Lingbo Li, Leslie Kanthan, Michail Basios, Fan Wu, Manal Adham, Vitali Avagyan, Alexis Butler, Paul Brookes, Rafail Giavrimis, Buhong Liu, Chrystalla Pavlou, Matthew Truscott, Vardan Voskanyan

Additionally, a key feature of evoML is that it embeds code and model optimisation into the model development process, and includes multi-objective optimisation capabilities.

Navigate

DC-CCL: Device-Cloud Collaborative Controlled Learning for Large Vision Models

no code implementations18 Mar 2023 Yucheng Ding, Chaoyue Niu, Fan Wu, Shaojie Tang, Chengfei Lyu, Guihai Chen

In this work, we propose a device-cloud collaborative controlled learning framework, called DC-CCL, enabling a cloud-side large vision model that cannot be directly deployed on the mobile device to still benefit from the device-side local samples.

Knowledge Distillation

Factor Graph Neural Networks

no code implementations NeurIPS 2020 Zhen Zhang, Mohammed Haroon Dupty, Fan Wu, Javen Qinfeng Shi, Wee Sun Lee

In recent years, we have witnessed a surge of Graph Neural Networks (GNNs), most of which can learn powerful representations in an end-to-end fashion with great success in many real-world applications.

Representation Learning

Privately Aligning Language Models with Reinforcement Learning

no code implementations25 Oct 2023 Fan Wu, Huseyin A. Inan, Arturs Backurs, Varun Chandrasekaran, Janardhan Kulkarni, Robert Sim

Positioned between pre-training and user deployment, aligning large language models (LLMs) through reinforcement learning (RL) has emerged as a prevailing strategy for training instruction following-models such as ChatGPT.

Instruction Following Privacy Preserving +3

ECLM: Efficient Edge-Cloud Collaborative Learning with Continuous Environment Adaptation

no code implementations18 Nov 2023 Yan Zhuang, Zhenzhe Zheng, Yunfeng Shao, Bingshuai Li, Fan Wu, Guihai Chen

In this paper, we propose ECLM, an edge-cloud collaborative learning framework for rapid model adaptation for dynamic edge environments.

A collaboration of multi-agent model using an interactive interface

1 code implementation journal 2022 Jingchen Li, Fan Wu, Haobin Shi, Kao-Shing Hwang

This work investigates the effect of noises in multi-agent environments and proposes a multi-agent actor-critic with collaboration (MACC) model.

Multi-agent Reinforcement Learning

SPT: Spectral Transformer for Red Giant Stars Age and Mass Estimation

no code implementations10 Jan 2024 Mengmeng Zhang, Fan Wu, Yude Bu, Shanshan Li, Zhenping Yi, Meng Liu, Xiaoming Kong

The age and mass of red giants are essential for understanding the structure and evolution of the Milky Way.

Astronomy

Trajectory-wise Iterative Reinforcement Learning Framework for Auto-bidding

no code implementations23 Feb 2024 Haoming Li, Yusen Huo, Shuai Dou, Zhenzhe Zheng, Zhilin Zhang, Chuan Yu, Jian Xu, Fan Wu

The trained policy can subsequently be deployed for further data collection, resulting in an iterative training framework, which we refer to as iterative offline RL.

Offline RL reinforcement-learning +2

MEBS: Multi-task End-to-end Bid Shading for Multi-slot Display Advertising

no code implementations5 Mar 2024 Zhen Gong, Lvyin Niu, Yang Zhao, Miao Xu, Zhenzhe Zheng, Haoqi Zhang, Zhilin Zhang, Fan Wu, Rongquan Bai, Chuan Yu, Jian Xu, Bo Zheng

Through extensive offline and online experiments, we demonstrate the effectiveness and efficiency of our method, and we obtain a 7. 01% lift in Gross Merchandise Volume, a 7. 42% lift in Return on Investment, and a 3. 26% lift in ad buy count.

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