Search Results for author: Yonggang Wen

Found 52 papers, 22 papers with code

Confronting Reward Overoptimization for Diffusion Models: A Perspective of Inductive and Primacy Biases

no code implementations13 Feb 2024 Ziyi Zhang, Sen Zhang, Yibing Zhan, Yong Luo, Yonggang Wen, DaCheng Tao

Then, we surprisingly discover that dormant neurons in our critic model act as a regularization against overoptimization, while active neurons reflect primacy bias in this setting.

Denoising Inductive Bias

PartSeg: Few-shot Part Segmentation via Part-aware Prompt Learning

no code implementations24 Aug 2023 Mengya Han, Heliang Zheng, Chaoyue Wang, Yong Luo, Han Hu, Jing Zhang, Yonggang Wen

In this work, we address the task of few-shot part segmentation, which aims to segment the different parts of an unseen object using very few labeled examples.

Language Modelling Segmentation

Rethinking the Localization in Weakly Supervised Object Localization

no code implementations11 Aug 2023 Rui Xu, Yong Luo, Han Hu, Bo Du, Jialie Shen, Yonggang Wen

Weakly supervised object localization (WSOL) is one of the most popular and challenging tasks in computer vision.

Object Weakly-Supervised Object Localization

MAS: Towards Resource-Efficient Federated Multiple-Task Learning

1 code implementation ICCV 2023 Weiming Zhuang, Yonggang Wen, Lingjuan Lyu, Shuai Zhang

Then, we present our new approach, MAS (Merge and Split), to optimize the performance of training multiple simultaneous FL tasks.

Federated Learning

FHA-Kitchens: A Novel Dataset for Fine-Grained Hand Action Recognition in Kitchen Scenes

1 code implementation19 Jun 2023 Ting Zhe, YongQian Li, Jing Zhang, Yong Luo, Han Hu, Bo Du, Yonggang Wen, DaCheng Tao

We represent the action information in each hand interaction region as a triplet, resulting in a total of 878 action triplets.

Action Recognition Domain Generalization +3

Boosting Distributed Full-graph GNN Training with Asynchronous One-bit Communication

no code implementations2 Mar 2023 Meng Zhang, Qinghao Hu, Peng Sun, Yonggang Wen, Tianwei Zhang

Training Graph Neural Networks (GNNs) on large graphs is challenging due to the conflict between the high memory demand and limited GPU memory.

Quantization

FedABC: Targeting Fair Competition in Personalized Federated Learning

no code implementations15 Feb 2023 Dui Wang, Li Shen, Yong Luo, Han Hu, Kehua Su, Yonggang Wen, DaCheng Tao

In particular, we adopt the ``one-vs-all'' training strategy in each client to alleviate the unfair competition between classes by constructing a personalized binary classification problem for each class.

Binary Classification Personalized Federated Learning

Machine Learning for a Sustainable Energy Future

no code implementations19 Oct 2022 Zhenpeng Yao, Yanwei Lum, Andrew Johnston, Luis Martin Mejia-Mendoza, Xin Zhou, Yonggang Wen, Alan Aspuru-Guzik, Edward H. Sargent, Zhi Wei Seh

Transitioning from fossil fuels to renewable energy sources is a critical global challenge; it demands advances at the levels of materials, devices, and systems for the efficient harvesting, storage, conversion, and management of renewable energy.

Management

Not All Instances Contribute Equally: Instance-adaptive Class Representation Learning for Few-Shot Visual Recognition

no code implementations7 Sep 2022 Mengya Han, Yibing Zhan, Yong Luo, Bo Du, Han Hu, Yonggang Wen, DaCheng Tao

To address the above issues, we propose a novel metric-based meta-learning framework termed instance-adaptive class representation learning network (ICRL-Net) for few-shot visual recognition.

Meta-Learning Representation Learning

Smart Multi-tenant Federated Learning

no code implementations9 Jul 2022 Weiming Zhuang, Yonggang Wen, Shuai Zhang

In this work, we propose a smart multi-tenant FL system, MuFL, to effectively coordinate and execute simultaneous training activities.

Federated Learning

Optimizing Performance of Federated Person Re-identification: Benchmarking and Analysis

2 code implementations24 May 2022 Weiming Zhuang, Xin Gan, Yonggang Wen, Shuai Zhang

Based on these insights, we propose three optimization approaches: (1) We adopt knowledge distillation to facilitate the convergence of FedReID by better transferring knowledge from clients to the server; (2) We introduce client clustering to improve the performance of large datasets by aggregating clients with similar data distributions; (3) We propose cosine distance weight to elevate performance by dynamically updating the weights for aggregation depending on how well models are trained in clients.

Benchmarking Federated Learning +2

Divergence-aware Federated Self-Supervised Learning

1 code implementation ICLR 2022 Weiming Zhuang, Yonggang Wen, Shuai Zhang

Using the framework, our study uncovers unique insights of FedSSL: 1) stop-gradient operation, previously reported to be essential, is not always necessary in FedSSL; 2) retaining local knowledge of clients in FedSSL is particularly beneficial for non-IID data.

Federated Learning Federated Unsupervised Learning +1

Federated Unsupervised Domain Adaptation for Face Recognition

no code implementations9 Apr 2022 Weiming Zhuang, Xin Gan, Yonggang Wen, Xuesen Zhang, Shuai Zhang, Shuai Yi

To address this problem, we propose federated unsupervised domain adaptation for face recognition, FedFR.

Clustering Face Recognition +2

Characterization and Prediction of Deep Learning Workloads in Large-Scale GPU Datacenters

1 code implementation3 Sep 2021 Qinghao Hu, Peng Sun, Shengen Yan, Yonggang Wen, Tianwei Zhang

Modern GPU datacenters are critical for delivering Deep Learning (DL) models and services in both the research community and industry.

Management Scheduling

Collaborative Unsupervised Visual Representation Learning from Decentralized Data

1 code implementation ICCV 2021 Weiming Zhuang, Xin Gan, Yonggang Wen, Shuai Zhang, Shuai Yi

In this framework, each party trains models from unlabeled data independently using contrastive learning with an online network and a target network.

Contrastive Learning Federated Learning +3

Joint Optimization in Edge-Cloud Continuum for Federated Unsupervised Person Re-identification

1 code implementation14 Aug 2021 Weiming Zhuang, Yonggang Wen, Shuai Zhang

We present FedUReID, a federated unsupervised person ReID system to learn person ReID models without any labels while preserving privacy.

Federated Learning Unsupervised Person Re-Identification

Are Missing Links Predictable? An Inferential Benchmark for Knowledge Graph Completion

1 code implementation ACL 2021 Yixin Cao, Xiang Ji, Xin Lv, Juanzi Li, Yonggang Wen, Hanwang Zhang

We present InferWiki, a Knowledge Graph Completion (KGC) dataset that improves upon existing benchmarks in inferential ability, assumptions, and patterns.

Knowledge Graph Completion

Exploring Sequence Feature Alignment for Domain Adaptive Detection Transformers

1 code implementation27 Jul 2021 Wen Wang, Yang Cao, Jing Zhang, Fengxiang He, Zheng-Jun Zha, Yonggang Wen, DaCheng Tao

In DQFA, a novel domain query is used to aggregate and align global context from the token sequence of both domains.

Domain Adaptation Object +2

ModelPS: An Interactive and Collaborative Platform for Editing Pre-trained Models at Scale

1 code implementation18 May 2021 Yuanming Li, Huaizheng Zhang, Shanshan Jiang, Fan Yang, Yonggang Wen, Yong Luo

AI engineering has emerged as a crucial discipline to democratize deep neural network (DNN) models among software developers with a diverse background.

Model Editing

EasyFL: A Low-code Federated Learning Platform For Dummies

1 code implementation17 May 2021 Weiming Zhuang, Xin Gan, Yonggang Wen, Shuai Zhang

However, these platforms are complex to use and require a deep understanding of FL, which imposes high barriers to entry for beginners, limits the productivity of researchers, and compromises deployment efficiency.

Federated Learning Privacy Preserving

Towards Unsupervised Domain Adaptation for Deep Face Recognition under Privacy Constraints via Federated Learning

no code implementations17 May 2021 Weiming Zhuang, Xin Gan, Yonggang Wen, Xuesen Zhang, Shuai Zhang, Shuai Yi

To this end, FedFR forms an end-to-end training pipeline: (1) pre-train in the source domain; (2) predict pseudo labels by clustering in the target domain; (3) conduct domain-constrained federated learning across two domains.

Clustering Face Recognition +2

A Serverless Cloud-Fog Platform for DNN-Based Video Analytics with Incremental Learning

no code implementations5 Feb 2021 Huaizheng Zhang, Meng Shen, Yizheng Huang, Yonggang Wen, Yong Luo, Guanyu Gao, Kyle Guan

To save bandwidth and reduce RTT, VPaaS provides a new video streaming protocol that only sends low-quality video to the cloud.

Incremental Learning Management

On the Practicality of Differential Privacy in Federated Learning by Tuning Iteration Times

no code implementations11 Jan 2021 Yao Fu, Yipeng Zhou, Di wu, Shui Yu, Yonggang Wen, Chao Li

Then, we theoretically derive: 1) the conditions for the DP based FedAvg to converge as the number of global iterations (GI) approaches infinity; 2) the method to set the number of local iterations (LI) to minimize the negative influence of DP noises.

Federated Learning

Learning Relation Prototype from Unlabeled Texts for Long-tail Relation Extraction

1 code implementation27 Nov 2020 Yixin Cao, Jun Kuang, Ming Gao, Aoying Zhou, Yonggang Wen, Tat-Seng Chua

In this paper, we propose a general approach to learn relation prototypesfrom unlabeled texts, to facilitate the long-tail relation extraction by transferring knowledge from the relation types with sufficient trainingdata.

Relation Relation Extraction +1

Privacy-preserving Collaborative Learning with Automatic Transformation Search

3 code implementations CVPR 2021 Wei Gao, Shangwei Guo, Tianwei Zhang, Han Qiu, Yonggang Wen, Yang Liu

Comprehensive evaluations demonstrate that the policies discovered by our method can defeat existing reconstruction attacks in collaborative learning, with high efficiency and negligible impact on the model performance.

Data Augmentation Privacy Preserving

InferBench: Understanding Deep Learning Inference Serving with an Automatic Benchmarking System

no code implementations4 Nov 2020 Huaizheng Zhang, Yizheng Huang, Yonggang Wen, Jianxiong Yin, Kyle Guan

Our system design follows the best practice in DL clusters operations to expedite day-to-day DL service evaluation efforts by the developers.

Benchmarking

Performance Optimization for Federated Person Re-identification via Benchmark Analysis

2 code implementations26 Aug 2020 Weiming Zhuang, Yonggang Wen, Xuesen Zhang, Xin Gan, Daiying Yin, Dongzhan Zhou, Shuai Zhang, Shuai Yi

Then we propose two optimization methods: (1) To address the unbalanced weight problem, we propose a new method to dynamically change the weights according to the scale of model changes in clients in each training round; (2) To facilitate convergence, we adopt knowledge distillation to refine the server model with knowledge generated from client models on a public dataset.

Federated Learning Knowledge Distillation +2

MLModelCI: An Automatic Cloud Platform for Efficient MLaaS

2 code implementations9 Jun 2020 Huaizheng Zhang, Yuanming Li, Yizheng Huang, Yonggang Wen, Jianxiong Yin, Kyle Guan

MLModelCI provides multimedia researchers and developers with a one-stop platform for efficient machine learning (ML) services.

Hysia: Serving DNN-Based Video-to-Retail Applications in Cloud

2 code implementations9 Jun 2020 Huaizheng Zhang, Yuanming Li, Qiming Ai, Yong Luo, Yonggang Wen, Yichao Jin, Nguyen Binh Duong Ta

Combining \underline{v}ideo streaming and online \underline{r}etailing (V2R) has been a growing trend recently.

Video Retrieval Video-to-Shop

Kalibre: Knowledge-based Neural Surrogate Model Calibration for Data Center Digital Twins

no code implementations29 Jan 2020 Ruihang Wang, Xin Zhou, Linsen Dong, Yonggang Wen, Rui Tan, Li Chen, Guan Wang, Feng Zeng

However, in the context of CFD, each search step requires long-lasting CFD model's iterated solving, rendering these approaches impractical with increased model complexity.

Management

Look, Read and Feel: Benchmarking Ads Understanding with Multimodal Multitask Learning

no code implementations21 Dec 2019 Huaizheng Zhang, Yong Luo, Qiming Ai, Yonggang Wen

A multitask loss function is also designed to train both the topic and sentiment prediction models jointly in an end-to-end manner.

Benchmarking

A Survey of Predictive Maintenance: Systems, Purposes and Approaches

no code implementations12 Dec 2019 Tianwen Zhu, Yongyi Ran, Xin Zhou, Yonggang Wen

This paper highlights the importance of maintenance techniques in the coming industrial revolution, reviews the evolution of maintenance techniques, and presents a comprehensive literature review on the latest advancement of maintenance techniques, i. e., Predictive Maintenance (PdM), with emphasis on system architectures, optimization objectives, and optimization methods.

Soft-ranking Label Encoding for Robust Facial Age Estimation

no code implementations9 Jun 2019 Xusheng Zeng, Changxing Ding, Yonggang Wen, DaCheng Tao

Moreover, we also carefully analyze existing evaluation protocols for age estimation, finding that the overlap in identity between the training and testing sets affects the relative performance of different age encoding methods.

Age Estimation MORPH

Baconian: A Unified Open-source Framework for Model-Based Reinforcement Learning

2 code implementations23 Apr 2019 Linsen Dong, Guanyu Gao, Xinyi Zhang, Liang-Yu Chen, Yonggang Wen

Model-Based Reinforcement Learning (MBRL) is one category of Reinforcement Learning (RL) algorithms which can improve sampling efficiency by modeling and approximating system dynamics.

Autonomous Driving Model-based Reinforcement Learning +2

Transferring Knowledge Fragments for Learning Distance Metric from A Heterogeneous Domain

no code implementations8 Apr 2019 Yong Luo, Yonggang Wen, Tongliang Liu, DaCheng Tao

Some existing heterogeneous transfer learning (HTL) approaches can learn target distance metric by usually transforming the samples of source and target domain into a common subspace.

Metric Learning Transfer Learning

Multi-view Vector-valued Manifold Regularization for Multi-label Image Classification

no code implementations8 Apr 2019 Yong Luo, DaCheng Tao, Chang Xu, Chao Xu, Hong Liu, Yonggang Wen

In computer vision, image datasets used for classification are naturally associated with multiple labels and comprised of multiple views, because each image may contain several objects (e. g. pedestrian, bicycle and tree) and is properly characterized by multiple visual features (e. g. color, texture and shape).

General Classification Multi-Label Image Classification

Heterogeneous Multi-task Metric Learning across Multiple Domains

no code implementations8 Apr 2019 Yong Luo, Yonggang Wen, DaCheng Tao

Heterogeneous transfer learning approaches can be adopted to remedy this drawback by deriving a metric from the learned transformation across different domains.

Metric Learning Scene Classification +2

Cost-Sensitive Feature Selection by Optimizing F-Measures

no code implementations4 Apr 2019 Meng Liu, Chang Xu, Yong Luo, Chao Xu, Yonggang Wen, DaCheng Tao

Feature selection is beneficial for improving the performance of general machine learning tasks by extracting an informative subset from the high-dimensional features.

feature selection

Optimizing Network Performance for Distributed DNN Training on GPU Clusters: ImageNet/AlexNet Training in 1.5 Minutes

1 code implementation19 Feb 2019 Peng Sun, Wansen Feng, Ruobing Han, Shengen Yan, Yonggang Wen

To address this problem, we propose a communication backend named GradientFlow for distributed DNN training, and employ a set of network optimization techniques.

Distributed, Parallel, and Cluster Computing

Energy-Efficient Thermal Comfort Control in Smart Buildings via Deep Reinforcement Learning

2 code implementations15 Jan 2019 Guanyu Gao, Jie Li, Yonggang Wen

We formulate the building thermal control as a cost-minimization problem which jointly considers the energy consumption of HVAC and the thermal comfort of the occupants.

reinforcement-learning Reinforcement Learning (RL)

Transfer Metric Learning: Algorithms, Applications and Outlooks

no code implementations9 Oct 2018 Yong Luo, Yonggang Wen, Ling-Yu Duan, DaCheng Tao

Distance metric learning (DML) aims to find an appropriate way to reveal the underlying data relationship.

Metric Learning

Intelligent Trainer for Model-Based Reinforcement Learning

1 code implementation24 May 2018 Yuanlong Li, Linsen Dong, Xin Zhou, Yonggang Wen, Kyle Guan

Model-based reinforcement learning (MBRL) has been proposed as a promising alternative solution to tackle the high sampling cost challenge in the canonical reinforcement learning (RL), by leveraging a learned model to generate synthesized data for policy training purpose.

Model-based Reinforcement Learning OpenAI Gym +2

A Survey on Consensus Mechanisms and Mining Strategy Management in Blockchain Networks

no code implementations7 May 2018 Wenbo Wang, Dinh Thai Hoang, Peizhao Hu, Zehui Xiong, Dusit Niyato, Ping Wang, Yonggang Wen, Dong In Kim

This survey is motivated by the lack of a comprehensive literature review on the development of decentralized consensus mechanisms in blockchain networks.

Cryptography and Security

Transforming Cooling Optimization for Green Data Center via Deep Reinforcement Learning

no code implementations15 Sep 2017 Yuanlong Li, Yonggang Wen, Kyle Guan, DaCheng Tao

Specifically, we propose an end-to-end cooling control algorithm (CCA) that is based on the actor-critic framework and an off-policy offline version of the deep deterministic policy gradient (DDPG) algorithm.

Management reinforcement-learning +1

Power Data Classification: A Hybrid of a Novel Local Time Warping and LSTM

no code implementations15 Aug 2016 Yuanlong Li, Han Hu, Yonggang Wen, Jun Zhang

Finally, using the power consumption data from a real data center, we show that the proposed LTW can improve the classification accuracy of DTW from about 84% to 90%.

Classification General Classification +3

Tensor Canonical Correlation Analysis for Multi-view Dimension Reduction

3 code implementations9 Feb 2015 Yong Luo, DaCheng Tao, Yonggang Wen, Kotagiri Ramamohanarao, Chao Xu

As a consequence, the high order correlation information contained in the different views is explored and thus a more reliable common subspace shared by all features can be obtained.

Dimensionality Reduction MULTI-VIEW LEARNING

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