Search Results for author: Tao Zhang

Found 74 papers, 10 papers with code

ActPerFL: Active Personalized Federated Learning

no code implementations FL4NLP (ACL) 2022 Huili Chen, Jie Ding, Eric Tramel, Shuang Wu, Anit Kumar Sahu, Salman Avestimehr, Tao Zhang

Inspired by Bayesian hierarchical models, we develop ActPerFL, a self-aware personalized FL method where each client can automatically balance the training of its local personal model and the global model that implicitly contributes to other clients’ training.

Personalized Federated Learning

InfoAT: Improving Adversarial Training Using the Information Bottleneck Principle

no code implementations23 Jun 2022 Mengting Xu, Tao Zhang, Zhongnian Li, Daoqiang Zhang

Therefore, guaranteeing the robustness of hard examples is crucial for improving the final robustness of the model.

Hybridization of evolutionary algorithm and deep reinforcement learning for multi-objective orienteering optimization

no code implementations21 Jun 2022 Wei Liu, Rui Wang, Tao Zhang, Kaiwen Li, Wenhua Li, Hisao Ishibuchi

Multi-objective orienteering problems (MO-OPs) are classical multi-objective routing problems and have received a lot of attention in the past decades.

Problem Decomposition reinforcement-learning

CREAM: Weakly Supervised Object Localization via Class RE-Activation Mapping

1 code implementation CVPR 2022 Jilan Xu, Junlin Hou, Yuejie Zhang, Rui Feng, Rui-Wei Zhao, Tao Zhang, Xuequan Lu, Shang Gao

In this paper, we empirically prove that this problem is associated with the mixup of the activation values between less discriminative foreground regions and the background.

Weakly-Supervised Object Localization

Deep Reinforcement Learning for Orienteering Problems Based on Decomposition

no code implementations25 Apr 2022 Wei Liu, Tao Zhang, Rui Wang, Kaiwen Li, Wenhua Li, Kang Yang

A dynamic pointer network (DYPN) is introduced as the TSP solver, which takes city locations as inputs and immediately outputs a permutation of nodes.

reinforcement-learning Traveling Salesman Problem

Deep Reinforcement Learning for Online Routing of Unmanned Aerial Vehicles with Wireless Power Transfer

no code implementations25 Apr 2022 Kaiwen Li, Tao Zhang, Rui Wang, Ling Wang

The model is trained using a deep reinforcement learning method offline, and is used to optimize the UAV routing problem online.

Combinatorial Optimization reinforcement-learning

Self-Aware Personalized Federated Learning

no code implementations17 Apr 2022 Huili Chen, Jie Ding, Eric Tramel, Shuang Wu, Anit Kumar Sahu, Salman Avestimehr, Tao Zhang

In the context of personalized federated learning (FL), the critical challenge is to balance local model improvement and global model tuning when the personal and global objectives may not be exactly aligned.

Personalized Federated Learning

SuperMVS: Non-Uniform Cost Volume For High-Resolution Multi-View Stereo

no code implementations27 Mar 2022 Tao Zhang

In this paper, we propose a free-moving hypothesis plane method for dynamic and non-uniform sampling in a wide depth range to build the cost volume, which not only greatly reduces the number of planes but also finers sampling, for both of reducing computational cost and improving accuracy, named Non-Uniform Cost Volume.

Leveraging Search History for Improving Person-Job Fit

no code implementations27 Mar 2022 Yupeng Hou, Xingyu Pan, Wayne Xin Zhao, Shuqing Bian, Yang song, Tao Zhang, Ji-Rong Wen

As the core technique of online recruitment platforms, person-job fit can improve hiring efficiency by accurately matching job positions with qualified candidates.

Text Matching

RRL:Regional Rotation Layer in Convolutional Neural Networks

no code implementations25 Feb 2022 Zongbo Hao, Tao Zhang, Mingwang Chen, Kaixu Zhou

Known solutions include the enhancement of training data and the increase of rotation invariance by globally merging the rotation equivariant features.

Image Classification object-detection +1

Federated Learning Challenges and Opportunities: An Outlook

no code implementations1 Feb 2022 Jie Ding, Eric Tramel, Anit Kumar Sahu, Shuang Wu, Salman Avestimehr, Tao Zhang

Federated learning (FL) has been developed as a promising framework to leverage the resources of edge devices, enhance customers' privacy, comply with regulations, and reduce development costs.

Federated Learning

End-to-End Quality-of-Service Assurance with Autonomous Systems: 5G/6G Case Study

no code implementations31 Jan 2022 Van Sy Mai, Richard J. La, Tao Zhang, Abdella Battou

This paper presents a novel framework and a distributed algorithm that can enable ANs and CNs to autonomously "cooperate" with each other to dynamically negotiate their local QoS budgets and to collectively meet E2E QoS goals by sharing only their estimates of the global constraint functions, without disclosing their local decision variables.

Distributed Optimization

Scale-Invariant Adversarial Attack for Evaluating and Enhancing Adversarial Defenses

no code implementations29 Jan 2022 Mengting Xu, Tao Zhang, Zhongnian Li, Daoqiang Zhang

Further, we propose Scale-Invariant (SI) adversarial defense mechanism based on the cosine angle matrix, which can be embedded into the popular adversarial defenses.

Adversarial Attack Adversarial Defense

Bayesian Promised Persuasion: Dynamic Forward-Looking Multiagent Delegation with Informational Burning

no code implementations16 Jan 2022 Tao Zhang, Quanyan Zhu

A revelation-principle-like design regime is established to show that the persuasion with belief hierarchies can be fully characterized by correlating the randomization of the agents' local BPD mechanisms with the persuasion as a direct recommendation of the future promises.

End-to-end Alexa Device Arbitration

no code implementations8 Dec 2021 Jarred Barber, Yifeng Fan, Tao Zhang

We introduce a variant of the speaker localization problem, which we call device arbitration.

MedRDF: A Robust and Retrain-Less Diagnostic Framework for Medical Pretrained Models Against Adversarial Attack

no code implementations29 Nov 2021 Mengting Xu, Tao Zhang, Daoqiang Zhang

However, the defense methods that have good effect in natural images may not be suitable for medical diagnostic tasks.

Adversarial Attack

Pre-training Graph Neural Network for Cross Domain Recommendation

no code implementations16 Nov 2021 Chen Wang, Yueqing Liang, Zhiwei Liu, Tao Zhang, Philip S. Yu

Then, we transfer the pre-trained graph encoder to initialize the node embeddings on the target domain, which benefits the fine-tuning of the single domain recommender system on the target domain.

Graph Representation Learning Recommendation Systems

FedProc: Prototypical Contrastive Federated Learning on Non-IID data

no code implementations25 Sep 2021 Xutong Mu, Yulong Shen, Ke Cheng, Xueli Geng, Jiaxuan Fu, Tao Zhang, Zhiwei Zhang

In this paper, we propose FedProc: prototypical contrastive federated learning, which is a simple and effective federated learning framework.

Federated Learning Image Classification

M3D-VTON: A Monocular-to-3D Virtual Try-On Network

1 code implementation ICCV 2021 Fuwei Zhao, Zhenyu Xie, Michael Kampffmeyer, Haoye Dong, Songfang Han, Tianxiang Zheng, Tao Zhang, Xiaodan Liang

Virtual 3D try-on can provide an intuitive and realistic view for online shopping and has a huge potential commercial value.

Virtual Try-on

Informational Design of Dynamic Multi-Agent System

no code implementations7 May 2021 Tao Zhang, Quanyan Zhu

We propose a direct information design approach that incentivizes each agent to select the signal sent by the principal, such that the design process avoids the predictions of the agents' strategic selection behaviors.

Low Pass Filter for Anti-aliasing in Temporal Action Localization

no code implementations23 Apr 2021 Cece Jin, Yuanqi Chen, Ge Li, Tao Zhang, Thomas Li

This paper aims to verify the existence of aliasing in TAL methods and investigate utilizing low pass filters to solve this problem by inhibiting the high-frequency band.

Temporal Action Localization

Towards Evaluating the Robustness of Deep Diagnostic Models by Adversarial Attack

1 code implementation5 Mar 2021 Mengting Xu, Tao Zhang, Zhongnian Li, Mingxia Liu, Daoqiang Zhang

Deep learning models (with neural networks) have been widely used in challenging tasks such as computer-aided disease diagnosis based on medical images.

Adversarial Attack Multi-Label Classification

On the Equilibrium Elicitation of Markov Games Through Information Design

no code implementations14 Feb 2021 Tao Zhang, Quanyan Zhu

An obedient principle is established which states that it is without loss of generality to focus on the direct information design when the information design incentivizes each agent to select the signal sent by the designer, such that the design process avoids the predictions of the agents' strategic selection behaviors.

Hyperspectral Image Denoising With Realistic Data

1 code implementation ICCV 2021 Tao Zhang, Ying Fu, Cheng Li

On the other hand, we propose an accurate HSI noise model which matches the distribution of real data well and can be employed to synthesize realistic dataset.

Hyperspectral Image Denoising Image Denoising

Generative Partial Visual-Tactile Fused Object Clustering

no code implementations28 Dec 2020 Tao Zhang, Yang Cong, Gan Sun, Jiahua Dong, Yuyang Liu, Zhengming Ding

More specifically, we first do partial visual and tactile features extraction from the partial visual and tactile data, respectively, and encode the extracted features in modality-specific feature subspaces.

Improving the Certified Robustness of Neural Networks via Consistency Regularization

no code implementations24 Dec 2020 Mengting Xu, Tao Zhang, Zhongnian Li, Daoqiang Zhang

A range of defense methods have been proposed to improve the robustness of neural networks on adversarial examples, among which provable defense methods have been demonstrated to be effective to train neural networks that are certifiably robust to the attacker.

On Front-end Gain Invariant Modeling for Wake Word Spotting

no code implementations13 Oct 2020 Yixin Gao, Noah D. Stein, Chieh-Chi Kao, Yunliang Cai, Ming Sun, Tao Zhang, Shiv Vitaladevuni

Since the WW model is trained with the AFE-processed audio data, its performance is sensitive to AFE variations, such as gain changes.

Investigating Constraint Relationship in Evolutionary Many-Constraint Optimization

no code implementations9 Oct 2020 Mengjun Ming, Rui Wang, Tao Zhang

This paper contributes to the treatment of extensive constraints in evolutionary many-constraint optimization through consideration of the relationships between pair-wise constraints.

Correlated Differential Privacy: Feature Selection in Machine Learning

no code implementations7 Oct 2020 Tao Zhang, Tianqing Zhu, Ping Xiong, Huan Huo, Zahir Tari, Wanlei Zhou

In this way, the impact of data correlation is relieved with the proposed feature selection scheme, and moreover, the privacy issue of data correlation in learning is guaranteed.

feature selection Privacy Preserving

Learning to Match Jobs with Resumes from Sparse Interaction Data using Multi-View Co-Teaching Network

no code implementations25 Sep 2020 Shuqing Bian, Xu Chen, Wayne Xin Zhao, Kun Zhou, Yupeng Hou, Yang song, Tao Zhang, Ji-Rong Wen

Compared with pure text-based matching models, the proposed approach is able to learn better data representations from limited or even sparse interaction data, which is more resistible to noise in training data.

Text Matching

Fairness in Semi-supervised Learning: Unlabeled Data Help to Reduce Discrimination

no code implementations25 Sep 2020 Tao Zhang, Tianqing Zhu, Jing Li, Mengde Han, Wanlei Zhou, Philip S. Yu

A set of experiments on real-world and synthetic datasets show that our method is able to use unlabeled data to achieve a better trade-off between accuracy and discrimination.

Ensemble Learning Fairness

Fairness Constraints in Semi-supervised Learning

no code implementations14 Sep 2020 Tao Zhang, Tianqing Zhu, Mengde Han, Jing Li, Wanlei Zhou, Philip S. Yu

Extensive experiments show that our method is able to achieve fair semi-supervised learning, and reach a better trade-off between accuracy and fairness than fair supervised learning.


Re-weighting and 1-Point RANSAC-Based PnP Solution to Handle Outliers

no code implementations16 Jul 2020 Haoyin Zhou, Tao Zhang, Jagadeesan Jayender

We propose a fast PnP solution named R1PPnP to handle outliers by utilizing a soft re-weighting mechanism and the 1-point RANSAC scheme.

Channel Compression: Rethinking Information Redundancy among Channels in CNN Architecture

no code implementations2 Jul 2020 Jinhua Liang, Tao Zhang, Guoqing Feng

Aiming at channel compression, a novel convolutional construction named compact convolution is proposed to embrace the progress in spatial convolution, channel grouping and pooling operation.

Acoustic Scene Classification Event Detection +4

Evolving Metric Learning for Incremental and Decremental Features

no code implementations27 Jun 2020 Jiahua Dong, Yang Cong, Gan Sun, Tao Zhang, Xu Tang, Xiaowei Xu

Online metric learning has been widely exploited for large-scale data classification due to the low computational cost.

Metric Learning

Bootstrap inference for quantile-based modal regression

no code implementations1 Jun 2020 Tao Zhang, Kengo Kato, David Ruppert

Specifically, we propose to estimate the conditional mode by minimizing the derivative of the estimated conditional quantile function defined by smoothing the linear quantile regression estimator, and develop two bootstrap methods, a novel pivotal bootstrap and the nonparametric bootstrap, for our conditional mode estimator.

Statistics Theory Methodology Statistics Theory

MZET: Memory Augmented Zero-Shot Fine-grained Named Entity Typing

no code implementations COLING 2020 Tao Zhang, Congying Xia, Chun-Ta Lu, Philip Yu

Named entity typing (NET) is a classification task of assigning an entity mention in the context with given semantic types.

Entity Typing

Adaptive Trajectory Estimation with Power Limited Steering Model under Perturbation Compensation

1 code implementation8 Dec 2019 Weipeng Li, Xiaogang Yang, Ruitao Lu, Jiwei Fan, Tao Zhang, Chuan He

The experiment of trajectory estimation demonstrates the convergence of AdaTE, and the better robust to the biased prior statistics and the observation drift compared with EKF, UKF and sparse MAP.

Information Theory Robotics Systems and Control Systems and Control Information Theory G.3.13; J.2.7

Visual Tactile Fusion Object Clustering

no code implementations21 Nov 2019 Tao Zhang, Yang Cong, Gan Sun, Qianqian Wang, Zhenming Ding

To effectively benefit both visual and tactile modalities for object clustering, in this paper, we propose a deep Auto-Encoder-like Non-negative Matrix Factorization framework for visual-tactile fusion clustering.

DARB: A Density-Aware Regular-Block Pruning for Deep Neural Networks

no code implementations19 Nov 2019 Ao Ren, Tao Zhang, Yuhao Wang, Sheng Lin, Peiyan Dong, Yen-Kuang Chen, Yuan Xie, Yanzhi Wang

As a further optimization, we propose a density-adaptive regular-block (DARB) pruning that outperforms prior structured pruning work with high pruning ratio and decoding efficiency.

Model Compression Network Pruning

Domain Adaptation for Person-Job Fit with Transferable Deep Global Match Network

no code implementations IJCNLP 2019 Shuqing Bian, Wayne Xin Zhao, Yang song, Tao Zhang, Ji-Rong Wen

Furthermore, we extend the match network and implement domain adaptation in three levels, sentence-level representation, sentence-level match, and global match.

Domain Adaptation

Hyperspectral Image Reconstruction Using Deep External and Internal Learning

no code implementations ICCV 2019 Tao Zhang, Ying Fu, Lizhi Wang, Hua Huang

To solve the low spatial and/or temporal resolution problem which the conventional hypelrspectral cameras often suffer from, coded snapshot hyperspectral imaging systems have attracted more attention recently.

Image Reconstruction

Representation Learning with Ordered Relation Paths for Knowledge Graph Completion

1 code implementation IJCNLP 2019 Yao Zhu, Hongzhi Liu, Zhonghai Wu, Yang song, Tao Zhang

Recently, a few methods take relation paths into consideration but pay less attention to the order of relations in paths which is important for reasoning.

Ranked #3 on Link Prediction on FB15k (MR metric)

Knowledge Graph Completion Link Prediction +1

FC$^2$N: Fully Channel-Concatenated Network for Single Image Super-Resolution

1 code implementation7 Jul 2019 Xiaole Zhao, Ying Liao, Tian He, Yulun Zhang, Yadong Wu, Tao Zhang

Most current image super-resolution (SR) methods based on convolutional neural networks (CNNs) use residual learning in network structural design, which favors to effective back propagation and hence improves SR performance by increasing model scale.

Image Super-Resolution Single Image Super Resolution

ARMIN: Towards a More Efficient and Light-weight Recurrent Memory Network

1 code implementation28 Jun 2019 Zhangheng Li, Jia-Xing Zhong, Jingjia Huang, Tao Zhang, Thomas Li, Ge Li

In recent years, memory-augmented neural networks(MANNs) have shown promising power to enhance the memory ability of neural networks for sequential processing tasks.

Data-Driven Machine Learning Techniques for Self-healing in Cellular Wireless Networks: Challenges and Solutions

no code implementations14 Jun 2019 Tao Zhang, Kun Zhu, Ekram Hossain

As an important component in SON, self-healing is defined as a network paradigm where the faults of target networks are mitigated or recovered by automatically triggering a series of actions such as detection, diagnosis and compensation.

Fault Detection

Deep Reinforcement Learning for Multi-objective Optimization

no code implementations6 Jun 2019 Kaiwen Li, Tao Zhang, Rui Wang

The solutions can be directly obtained by a simple forward calculation of the neural network; thereby, no iteration is required and the MOP can be always solved in a reasonable time.


A Hybrid Approach with Optimization and Metric-based Meta-Learner for Few-Shot Learning

no code implementations4 Apr 2019 Duo Wang, Yu Cheng, Mo Yu, Xiaoxiao Guo, Tao Zhang

The task-specific classifiers are required to be homogeneous-structured to ease the parameter prediction, so the meta-learning approaches could only handle few-shot learning problems where the tasks share a uniform number of classes.

Few-Shot Learning General Classification +3

Imbalanced Sentiment Classification Enhanced with Discourse Marker

no code implementations28 Mar 2019 Tao Zhang, Xing Wu, Meng Lin, Jizhong Han, Songlin Hu

Imbalanced data commonly exists in real world, espacially in sentiment-related corpus, making it difficult to train a classifier to distinguish latent sentiment in text data.

Classification Data Augmentation +2

SEGAN: Structure-Enhanced Generative Adversarial Network for Compressed Sensing MRI Reconstruction

no code implementations18 Feb 2019 Zhongnian Li, Tao Zhang, Peng Wan, Daoqiang Zhang

Generative Adversarial Networks (GANs) are powerful tools for reconstructing Compressed Sensing Magnetic Resonance Imaging (CS-MRI).

MRI Reconstruction

Acceleration of the NVT-flash calculation for multicomponent mixtures using deep neural network models

no code implementations27 Jan 2019 Yiteng Li, Tao Zhang, Shuyu Sun

Phase equilibrium calculation, also known as flash calculation, has been extensively applied in petroleum engineering, not only as a standalone application for separation process but also an integral component of compositional reservoir simulation.

Single MR Image Super-Resolution via Channel Splitting and Serial Fusion Network

no code implementations19 Jan 2019 Zhao Xiaole, Huali Zhang, Hangfei Liu, Yun Qin, Tao Zhang, Xueming Zou

Single image super-resolution (SISR), especially that based on deep learning techniques, is an effective and promising alternative technique to improve the current spatial resolution of magnetic resonance (MR) images.

Image Super-Resolution Single Image Super Resolution

Channel Splitting Network for Single MR Image Super-Resolution

no code implementations15 Oct 2018 Xiaole Zhao, Yulun Zhang, Tao Zhang, Xueming Zou

The proposed CSN model divides the hierarchical features into two branches, i. e., residual branch and dense branch, with different information transmissions.

Image Super-Resolution Single Image Super Resolution


no code implementations27 Sep 2018 Zhangheng Li, Jia-Xing Zhong, Jingjia Huang, Tao Zhang, Thomas Li, Ge Li

Processing sequential data with long term dependencies and learn complex transitions are two major challenges in many deep learning applications.

Joint Camera Spectral Sensitivity Selection and Hyperspectral Image Recovery

no code implementations ECCV 2018 Ying Fu, Tao Zhang, Yinqiang Zheng, Debing Zhang, Hua Huang

Hyperspectral image (HSI) recovery from a single RGB image has attracted much attention, whose performance has recently been shown to be sensitive to the camera spectral sensitivity (CSS).

Convolutional Neural Networks based Intra Prediction for HEVC

no code implementations17 Aug 2018 Wenxue Cui, Tao Zhang, Shengping Zhang, Feng Jiang, WangMeng Zuo, Debin Zhao

To overcome this problem, in this paper, an intra prediction convolutional neural network (IPCNN) is proposed for intra prediction, which exploits the rich context of the current block and therefore is capable of improving the accuracy of predicting the current block.

Step-by-step Erasion, One-by-one Collection: A Weakly Supervised Temporal Action Detector

no code implementations9 Jul 2018 Jia-Xing Zhong, Nannan Li, Weijie Kong, Tao Zhang, Thomas H. Li, Ge Li

Weakly supervised temporal action detection is a Herculean task in understanding untrimmed videos, since no supervisory signal except the video-level category label is available on training data.

Action Detection Temporal Localization

A Survey of Model Compression and Acceleration for Deep Neural Networks

no code implementations23 Oct 2017 Yu Cheng, Duo Wang, Pan Zhou, Tao Zhang

Methods of parameter pruning and quantization are described first, after that the other techniques are introduced.

Knowledge Distillation Model Compression +1

Limits on Axion Couplings from the first 80-day data of PandaX-II Experiment

no code implementations25 Jul 2017 Changbo Fu, Xiaopeng Zhou, Xun Chen, Yunhua Chen, Xiangyi Cui, Deqing Fang, Karl Giboni, Franco Giuliani, Ke Han, Xingtao Huang, Xiangdong Ji, Yonglin Ju, Siao Lei, Shaoli Li, Huaxuan Liu, Jianglai Liu, Yugang Ma, Yajun Mao, Xiangxiang Ren, Andi Tan, Hongwei Wang, Jimin Wang, Meng Wang, Qiuhong Wang, Siguang Wang, Xuming Wang, Zhou Wang, Shiyong Wu, Mengjiao Xiao, Pengwei Xie, Binbin Yan, Yong Yang, Jianfeng Yue, Hongguang Zhang, Tao Zhang, Li Zhao, Ning Zhou

We report new searches for the solar axions and galactic axion-like dark matter particles, using the first low-background data from PandaX-II experiment at China Jinping Underground Laboratory, corresponding to a total exposure of about $2. 7\times 10^4$ kg$\cdot$day.

High Energy Physics - Experiment Solar and Stellar Astrophysics High Energy Physics - Phenomenology

A Self-Adaptive Proposal Model for Temporal Action Detection based on Reinforcement Learning

1 code implementation22 Jun 2017 Jingjia Huang, Nannan Li, Tao Zhang, Ge Li

Existing action detection algorithms usually generate action proposals through an extensive search over the video at multiple temporal scales, which brings about huge computational overhead and deviates from the human perception procedure.

Action Detection Q-Learning +1

Bootstrapping Face Detection with Hard Negative Examples

no code implementations7 Aug 2016 Shaohua Wan, Zhijun Chen, Tao Zhang, Bo Zhang, Kong-kat Wong

Recently significant performance improvement in face detection was made possible by deeply trained convolutional networks.

Face Detection

Simulating user learning in authoritative technology adoption: An agent based model for council-led smart meter deployment planning in the UK

no code implementations20 Jul 2016 Tao Zhang, Peer-Olaf Siebers, Uwe Aickelin

In this paper we investigate user learning in authoritative technology adoption by developing an agent-based model using the case of council-led smart meter deployment in the UK City of Leeds.

Modelling Office Energy Consumption: An Agent Based Approach

no code implementations20 Jul 2016 Tao Zhang, Peer-Olaf Siebers, Uwe Aickelin

In this paper, we develop an agent-based model which integrates four important elements, i. e. organisational energy management policies/regulations, energy management technologies, electric appliances and equipment, and human behaviour, based on a case study, to simulate the energy consumption in office buildings.

Dynamic Privacy For Distributed Machine Learning Over Network

no code implementations14 Jan 2016 Tao Zhang, Quanyan Zhu

Privacy-preserving distributed machine learning becomes increasingly important due to the recent rapid growth of data.

Privacy Preserving

Modelling Electricity Consumption in Office Buildings: An Agent Based Approach

no code implementations31 May 2013 Tao Zhang, Peer-Olaf Siebers, Uwe Aickelin

In this paper, we develop an agent-based model which integrates four important elements, i. e. organisational energy management policies/regulations, energy management technologies, electric appliances and equipment, and human behaviour, to simulate the electricity consumption in office buildings.

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