Search Results for author: Tong Zhang

Found 243 papers, 64 papers with code

Toward Knowledge-Enriched Conversational Recommendation Systems

no code implementations NLP4ConvAI (ACL) 2022 Tong Zhang, Yong liu, Boyang Li, Peixiang Zhong, Chen Zhang, Hao Wang, Chunyan Miao

Conversational Recommendation Systems recommend items through language based interactions with users. In order to generate naturalistic conversations and effectively utilize knowledge graphs (KGs) containing background information, we propose a novel Bag-of-Entities loss, which encourages the generated utterances to mention concepts related to the item being recommended, such as the genre or director of a movie.

Knowledge Graphs Recommendation Systems +1

MulT: An End-to-End Multitask Learning Transformer

no code implementations17 May 2022 Deblina Bhattacharjee, Tong Zhang, Sabine Süsstrunk, Mathieu Salzmann

At the heart of our approach is a shared attention mechanism modeling the dependencies across the tasks.

Depth Estimation Edge Detection +2

Nearly Optimal Algorithms for Linear Contextual Bandits with Adversarial Corruptions

no code implementations13 May 2022 Jiafan He, Dongruo Zhou, Tong Zhang, Quanquan Gu

We show that for both known $C$ and unknown $C$ cases, our algorithm with proper choice of hyperparameter achieves a regret that nearly matches the lower bounds.

Multi-Armed Bandits

Deep Non-rigid Structure-from-Motion: A Sequence-to-Sequence Translation Perspective

no code implementations10 Apr 2022 Hui Deng, Tong Zhang, Yuchao Dai, Jiawei Shi, Yiran Zhong, Hongdong Li

In this paper, we propose to model deep NRSfM from a sequence-to-sequence translation perspective, where the input 2D frame sequence is taken as a whole to reconstruct the deforming 3D non-rigid shape sequence.

3D Reconstruction Frame +1

Leverage Your Local and Global Representations: A New Self-Supervised Learning Strategy

no code implementations31 Mar 2022 Tong Zhang, Congpei Qiu, Wei Ke, Sabine Süsstrunk, Mathieu Salzmann

In essence, this strategy ignores the fact that two crops may truly contain different image information, e. g., background and small objects, and thus tends to restrain the diversity of the learned representations.

Self-Supervised Learning Transfer Learning

Non-Linear Reinforcement Learning in Large Action Spaces: Structural Conditions and Sample-efficiency of Posterior Sampling

no code implementations15 Mar 2022 Alekh Agarwal, Tong Zhang

Provably sample-efficient Reinforcement Learning (RL) with rich observations and function approximation has witnessed tremendous recent progress, particularly when the underlying function approximators are linear.

RC-MVSNet: Unsupervised Multi-View Stereo with Neural Rendering

1 code implementation8 Mar 2022 Di Chang, Aljaž Božič, Tong Zhang, Qingsong Yan, Yingcong Chen, Sabine Süsstrunk, Matthias Nießner

Finding accurate correspondences among different views is the Achilles' heel of unsupervised Multi-View Stereo (MVS).

Neural Rendering

Pessimistic Minimax Value Iteration: Provably Efficient Equilibrium Learning from Offline Datasets

no code implementations15 Feb 2022 Han Zhong, Wei Xiong, Jiyuan Tan, LiWei Wang, Tong Zhang, Zhaoran Wang, Zhuoran Yang

When the dataset does not have uniform coverage over all policy pairs, finding an approximate NE involves challenges in three aspects: (i) distributional shift between the behavior policy and the optimal policy, (ii) function approximation to handle large state space, and (iii) minimax optimization for equilibrium solving.

Minimax Regret Optimization for Robust Machine Learning under Distribution Shift

no code implementations11 Feb 2022 Alekh Agarwal, Tong Zhang

We instead propose an alternative method called Minimax Regret Optimization (MRO), and show that under suitable conditions this method achieves uniformly low regret across all test distributions.

Learning Theory

Achieving Minimax Rates in Pool-Based Batch Active Learning

no code implementations11 Feb 2022 Claudio Gentile, Zhilei Wang, Tong Zhang

We consider a batch active learning scenario where the learner adaptively issues batches of points to a labeling oracle.

Active Learning Informativeness

Black-box Prompt Learning for Pre-trained Language Models

no code implementations21 Jan 2022 Shizhe Diao, Xuechun Li, Yong Lin, Zhichao Huang, Tong Zhang

Domain-specific fine-tuning strategies for large pre-trained models received vast attention in recent years.

Text Classification

OneDConv: Generalized Convolution For Transform-Invariant Representation

no code implementations15 Jan 2022 Tong Zhang, Haohan Weng, Ke Yi, C. L. Philip Chen

Convolutional Neural Networks (CNNs) have exhibited their great power in a variety of vision tasks.

A Novel Multi-Task Learning Method for Symbolic Music Emotion Recognition

no code implementations15 Jan 2022 Jibao Qiu, C. L. Philip Chen, Tong Zhang

In this paper, we present a simple multi-task framework for SMER, which incorporates the emotion recognition task with other emotion-related auxiliary tasks derived from the intrinsic structure of the music.

Emotion Recognition Language Modelling +2

Time Series Generation with Masked Autoencoder

no code implementations14 Jan 2022 Mengyue Zha, SiuTim Wong, Mengqi Liu, Tong Zhang, Kani Chen

This paper shows that masked autoencoder with extrapolator (ExtraMAE) is a scalable self-supervised model for time series generation.

Data Augmentation Imputation +3

IDEA: Interpretable Dynamic Ensemble Architecture for Time Series Prediction

no code implementations14 Jan 2022 Mengyue Zha, Kani Chen, Tong Zhang

We enhance the accuracy and generalization of univariate time series point prediction by an explainable ensemble on the fly.

Time Series Time Series Prediction

Frequency-Aware Contrastive Learning for Neural Machine Translation

no code implementations29 Dec 2021 Tong Zhang, Wei Ye, Baosong Yang, Long Zhang, Xingzhang Ren, Dayiheng Liu, Jinan Sun, Shikun Zhang, Haibo Zhang, Wen Zhao

Inspired by the observation that low-frequency words form a more compact embedding space, we tackle this challenge from a representation learning perspective.

Contrastive Learning Machine Translation +2

On the Impact of Hard Adversarial Instances on Overfitting in Adversarial Training

no code implementations14 Dec 2021 Chen Liu, Zhichao Huang, Mathieu Salzmann, Tong Zhang, Sabine Süsstrunk

This lets us show that the decay in generalization performance of adversarial training is a result of the model's attempt to fit hard adversarial instances.

A Provably Efficient Model-Free Posterior Sampling Method for Episodic Reinforcement Learning

no code implementations NeurIPS 2021 Christoph Dann, Mehryar Mohri, Tong Zhang, Julian Zimmert

Thompson Sampling is one of the most effective methods for contextual bandits and has been generalized to posterior sampling for certain MDP settings.

Multi-Armed Bandits reinforcement-learning

Optimizing Latent Space Directions For GAN-based Local Image Editing

1 code implementation24 Nov 2021 Ehsan Pajouheshgar, Tong Zhang, Sabine Süsstrunk

Generative Adversarial Network (GAN) based localized image editing can suffer from ambiguity between semantic attributes.


Efficient Neural Network Training via Forward and Backward Propagation Sparsification

1 code implementation NeurIPS 2021 Xiao Zhou, Weizhong Zhang, Zonghao Chen, Shizhe Diao, Tong Zhang

For the latter step, instead of using the chain rule based gradient estimators as in existing methods, we propose a variance reduced policy gradient estimator, which only requires two forward passes without backward propagation, thus achieving completely sparse training.

Why Stable Learning Works? A Theory of Covariate Shift Generalization

no code implementations3 Nov 2021 Renzhe Xu, Peng Cui, Zheyan Shen, Xingxuan Zhang, Tong Zhang

We first specify a set of variables, named minimal stable variable set, that is minimal and optimal to deal with covariate shift generalization for common loss functions, including the mean squared loss and binary cross entropy loss.

Eigencurve: Optimal Learning Rate Schedule for SGD on Quadratic Objectives with Skewed Hessian Spectrums

1 code implementation ICLR 2022 Rui Pan, Haishan Ye, Tong Zhang

Towards answering this reopened question, in this paper, we propose Eigencurve, the first family of learning rate schedules that can achieve minimax optimal convergence rates (up to a constant) for SGD on quadratic objectives when the eigenvalue distribution of the underlying Hessian matrix is skewed.

Image Classification

When is the Convergence Time of Langevin Algorithms Dimension Independent? A Composite Optimization Viewpoint

no code implementations5 Oct 2021 Yoav Freund, Yi-An Ma, Tong Zhang

There has been a surge of works bridging MCMC sampling and optimization, with a specific focus on translating non-asymptotic convergence guarantees for optimization problems into the analysis of Langevin algorithms in MCMC sampling.

Feel-Good Thompson Sampling for Contextual Bandits and Reinforcement Learning

no code implementations2 Oct 2021 Tong Zhang

In this setting, we show that the standard Thompson Sampling is not aggressive enough in exploring new actions, leading to suboptimality in some pessimistic situations.

Multi-Armed Bandits reinforcement-learning

Interest-based Item Representation Framework for Recommendation with Multi-Interests Capsule Network

no code implementations29 Sep 2021 Yanpeng Xie, Tong Zhang, Heng Zhang, Zhendong Qu

To make the framework model-agnostic, user Multi Interests Capsule Network is designed as an auxiliary task to jointly learn item-based item representations and interest-based item representations.

Recommendation Systems Representation Learning

HyperDQN: A Randomized Exploration Method for Deep Reinforcement Learning

no code implementations ICLR 2022 Ziniu Li, Yingru Li, Yushun Zhang, Tong Zhang, Zhi-Quan Luo

However, it is limited to the case where 1) a good feature is known in advance and 2) this feature is fixed during the training: if otherwise, RLSVI suffers an unbearable computational burden to obtain the posterior samples of the parameter in the $Q$-value function.

Efficient Exploration reinforcement-learning

Improving Adversarial Defense with Self-supervised Test-time Fine-tuning

no code implementations29 Sep 2021 Zhichao Huang, Chen Liu, Mathieu Salzmann, Sabine Süsstrunk, Tong Zhang

Although adversarial training and its variants currently constitute the most effective way to achieve robustness against adversarial attacks, their poor generalization limits their performance on the test samples.

Adversarial Defense

EllipseNet: Anchor-Free Ellipse Detection for Automatic Cardiac Biometrics in Fetal Echocardiography

1 code implementation26 Sep 2021 Jiancong Chen, Yingying Zhang, Jingyi Wang, Xiaoxue Zhou, Yihua He, Tong Zhang

In this paper, we present an anchor-free ellipse detection network, namely EllipseNet, which detects the cardiac and thoracic regions in ellipse and automatically calculates the CTR and cardiac axis for fetal cardiac biometrics in 4-chamber view.

Feature Correlation Aggregation: on the Path to Better Graph Neural Networks

no code implementations20 Sep 2021 Jieming Zhou, Tong Zhang, Pengfei Fang, Lars Petersson, Mehrtash Harandi

The core concept of GNNs is to find a representation by recursively aggregating the representations of a central node and those of its neighbors.

G-DetKD: Towards General Distillation Framework for Object Detectors via Contrastive and Semantic-guided Feature Imitation

no code implementations ICCV 2021 Lewei Yao, Renjie Pi, Hang Xu, Wei zhang, Zhenguo Li, Tong Zhang

In this paper, we investigate the knowledge distillation (KD) strategy for object detection and propose an effective framework applicable to both homogeneous and heterogeneous student-teacher pairs.

Knowledge Distillation Object Detection

Accelerating Edge Intelligence via Integrated Sensing and Communication

no code implementations20 Jul 2021 Tong Zhang, Shuai Wang, Guoliang Li, Fan Liu, Guangxu Zhu, Rui Wang

Conventionally, the sensing and communication stages are executed sequentially, which results in excessive amount of dataset generation and uploading time.

Near Optimal Stochastic Algorithms for Finite-Sum Unbalanced Convex-Concave Minimax Optimization

no code implementations3 Jun 2021 Luo Luo, Guangzeng Xie, Tong Zhang, Zhihua Zhang

This paper considers stochastic first-order algorithms for convex-concave minimax problems of the form $\min_{\bf x}\max_{\bf y}f(\bf x, \bf y)$, where $f$ can be presented by the average of $n$ individual components which are $L$-average smooth.

Multi-Hop Transformer for Document-Level Machine Translation

no code implementations NAACL 2021 Long Zhang, Tong Zhang, Haibo Zhang, Baosong Yang, Wei Ye, Shikun Zhang

Document-level neural machine translation (NMT) has proven to be of profound value for its effectiveness on capturing contextual information.

Document Level Machine Translation Document Translation +2

Universal Adder Neural Networks

no code implementations29 May 2021 Hanting Chen, Yunhe Wang, Chang Xu, Chao Xu, Chunjing Xu, Tong Zhang

The widely-used convolutions in deep neural networks are exactly cross-correlation to measure the similarity between input feature and convolution filters, which involves massive multiplications between float values.

Joint-DetNAS: Upgrade Your Detector with NAS, Pruning and Dynamic Distillation

no code implementations CVPR 2021 Lewei Yao, Renjie Pi, Hang Xu, Wei zhang, Zhenguo Li, Tong Zhang

For student morphism, weight inheritance strategy is adopted, allowing the student to flexibly update its architecture while fully utilize the predecessor's weights, which considerably accelerates the search; To facilitate dynamic distillation, an elastic teacher pool is trained via integrated progressive shrinking strategy, from which teacher detectors can be sampled without additional cost in subsequent searches.

Knowledge Distillation Neural Architecture Search +1

TransNAS-Bench-101: Improving Transferability and Generalizability of Cross-Task Neural Architecture Search

1 code implementation CVPR 2021 Yawen Duan, Xin Chen, Hang Xu, Zewei Chen, Xiaodan Liang, Tong Zhang, Zhenguo Li

While existing NAS methods mostly design architectures on a single task, algorithms that look beyond single-task search are surging to pursue a more efficient and universal solution across various tasks.

Neural Architecture Search Transfer Learning

KECRS: Towards Knowledge-Enriched Conversational Recommendation System

no code implementations18 May 2021 Tong Zhang, Yong liu, Peixiang Zhong, Chen Zhang, Hao Wang, Chunyan Miao

The chit-chat-based conversational recommendation systems (CRS) provide item recommendations to users through natural language interactions.

Entity Embeddings Knowledge Graphs +3

ZEN 2.0: Continue Training and Adaption for N-gram Enhanced Text Encoders

1 code implementation4 May 2021 Yan Song, Tong Zhang, Yonggang Wang, Kai-Fu Lee

Pre-trained text encoders have drawn sustaining attention in natural language processing (NLP) and shown their capability in obtaining promising results in different tasks.

Effective Sparsification of Neural Networks with Global Sparsity Constraint

1 code implementation CVPR 2021 Xiao Zhou, Weizhong Zhang, Hang Xu, Tong Zhang

Weight pruning is an effective technique to reduce the model size and inference time for deep neural networks in real-world deployments.

Geometry-aware data augmentation for monocular 3D object detection

no code implementations12 Apr 2021 Qing Lian, Botao Ye, Ruijia Xu, Weilong Yao, Tong Zhang

This paper focuses on monocular 3D object detection, one of the essential modules in autonomous driving systems.

Autonomous Driving Data Augmentation +1

Reinforced Attention for Few-Shot Learning and Beyond

no code implementations CVPR 2021 Jie Hong, Pengfei Fang, Weihao Li, Tong Zhang, Christian Simon, Mehrtash Harandi, Lars Petersson

Few-shot learning aims to correctly recognize query samples from unseen classes given a limited number of support samples, often by relying on global embeddings of images.

Few-Shot Learning Image Classification +1

Modeling Object Dissimilarity for Deep Saliency Prediction

no code implementations8 Apr 2021 Bahar Aydemir, Deblina Bhattacharjee, Seungryong Kim, Tong Zhang, Mathieu Salzmann, Sabine Süsstrunk

Saliency prediction has made great strides over the past two decades, with current techniques modeling low-level information, such as color, intensity and size contrasts, and high-level one, such as attention and gaze direction for entire objects.

Saliency Prediction

Uncertainty-aware Joint Salient Object and Camouflaged Object Detection

1 code implementation CVPR 2021 Aixuan Li, Jing Zhang, Yunqiu Lv, Bowen Liu, Tong Zhang, Yuchao Dai

Visual salient object detection (SOD) aims at finding the salient object(s) that attract human attention, while camouflaged object detection (COD) on the contrary intends to discover the camouflaged object(s) that hidden in the surrounding.

Object Detection Salient Object Detection

Few-Shot Human Motion Transfer by Personalized Geometry and Texture Modeling

1 code implementation CVPR 2021 Zhichao Huang, Xintong Han, Jia Xu, Tong Zhang

We present a new method for few-shot human motion transfer that achieves realistic human image generation with only a small number of appearance inputs.

Image Generation

Spatial-Temporal Tensor Graph Convolutional Network for Traffic Prediction

no code implementations10 Mar 2021 Xuran Xu, Tong Zhang, Chunyan Xu, Zhen Cui, Jian Yang

We further extend graph convolution into tensor space and propose a tensor graph convolution network to extract more discriminating features from spatial-temporal graph data.

Tensor Decomposition Traffic Prediction

Towards Unbiased COVID-19 Lesion Localisation and Segmentation via Weakly Supervised Learning

1 code implementation1 Mar 2021 Yang Yang, Jiancong Chen, Ruixuan Wang, Ting Ma, Lingwei Wang, Jie Chen, Wei-Shi Zheng, Tong Zhang

Despite tremendous efforts, it is very challenging to generate a robust model to assist in the accurate quantification assessment of COVID-19 on chest CT images.

Siamese Labels Auxiliary Network(SiLaNet)

no code implementations27 Feb 2021 Wenrui Gan, Zhulin Liu, C. L. Philip Chen, Tong Zhang

While in the testing phase, the auxiliary module should be removed.

DeEPCA: Decentralized Exact PCA with Linear Convergence Rate

no code implementations8 Feb 2021 Haishan Ye, Tong Zhang

This leads to a decentralized PCA algorithm called \texttt{DeEPCA}, which has a convergence rate similar to that of the centralized PCA, while achieving the best communication complexity among existing decentralized PCA algorithms.

Nondiscriminatory Treatment: a straightforward framework for multi-human parsing

no code implementations26 Jan 2021 Min Yan, Guoshan Zhang, Tong Zhang, Yueming Zhang

In inference time, we design a brand-new grouping post-processing method that relates each part instance with one single human instance and groups them together to obtain the final human-level parsing result.

Instance Segmentation Multi-Human Parsing +1

On Secure Degrees of Freedom of the MIMO Interference Channel with Local Output Feedback

no code implementations3 Jan 2021 Tong Zhang, Yinfei Xu, Shuai Wang, Miaowen Wen, Rui Wang

This paper studies the problem of sum-secure degrees of freedom (SDoF) of the (M, M, N, N) multiple-input multiple-output (MIMO) interference channel with local output feedback, so as to build an information-theoretic foundation and provide practical transmission schemes for 6G-enabled vehicles-to-vehicles (V2V).

Information Theory Information Theory

Graph Deformer Network

no code implementations1 Jan 2021 Wenting Zhao, Yuan Fang, Zhen Cui, Tong Zhang, Jian Yang, Wei Liu

In this paper, we propose a simple yet effective graph deformer network (GDN) to fulfill anisotropic convolution filtering on graphs, analogous to the standard convolution operation on images.

TransNAS-Bench-101: Improving Transferrability and Generalizability of Cross-Task Neural Architecture Search

2 code implementations1 Jan 2021 Yawen Duan, Xin Chen, Hang Xu, Zewei Chen, Xiaodan Liang, Tong Zhang, Zhenguo Li

While existing NAS methods mostly design architectures on one single task, algorithms that look beyond single-task search are surging to pursue a more efficient and universal solution across various tasks.

Neural Architecture Search Transfer Learning

Effective Training of Sparse Neural Networks under Global Sparsity Constraint

no code implementations1 Jan 2021 Xiao Zhou, Weizhong Zhang, Tong Zhang

An appealing feature of ProbMask is that the amounts of weight redundancy can be learned automatically via our constraint and thus we avoid the problem of tuning pruning rates individually for different layers in a network.

Invariant Batch Normalization for Multi-source Domain Generalization

no code implementations1 Jan 2021 Qing Lian, LIN Yong, Tong Zhang

We consider the domain generalization problem, where the test domain differs from the training domain.

Domain Generalization

Wasserstein Coupled Graph Learning for Cross-Modal Retrieval

no code implementations ICCV 2021 Yun Wang, Tong Zhang, Xueya Zhang, Zhen Cui, Yuge Huang, Pengcheng Shen, Shaoxin Li, Jian Yang

Then, a Wasserstein coupled dictionary, containing multiple pairs of counterpart graph keys with each key corresponding to one modality, is constructed for further feature learning.

Cross-Modal Retrieval Graph Embedding +1

Mathematical Models of Overparameterized Neural Networks

1 code implementation27 Dec 2020 Cong Fang, Hanze Dong, Tong Zhang

Deep learning has received considerable empirical successes in recent years.

Multi-modal AsynDGAN: Learn From Distributed Medical Image Data without Sharing Private Information

no code implementations15 Dec 2020 Qi Chang, Zhennan Yan, Lohendran Baskaran, Hui Qu, Yikai Zhang, Tong Zhang, Shaoting Zhang, Dimitris N. Metaxas

As deep learning technologies advance, increasingly more data is necessary to generate general and robust models for various tasks.

Evidence of topological nodal lines and surface states in the centrosymmetric superconductor SnTaS2

no code implementations7 Dec 2020 Wenqing Chen, Lulu Liu, Wentao Yang, Dong Chen, Zhengtai Liu, Yaobo Huang, Tong Zhang, Haijun Zhang, Zhonghao Liu, D. W. Shen

Utilizing angle-resolved photoemission spectroscopy and first-principles calculations, here, we demonstrate the existence of topological nodal-line states and drumheadlike surface states in centrosymmetric superconductor SnTaS2, which is a type-II superconductor with a critical transition temperature of about 3 K. The valence bands from Ta 5d orbitals and the conduction bands from Sn 5p orbitals cross each other, forming two nodal lines in the vicinity of the Fermi energy without the inclusion of spin-orbit coupling (SOC), protected by the spatial-inversion symmetry and time-reversal symmetry.


Residual Distillation: Towards Portable Deep Neural Networks without Shortcuts

no code implementations NeurIPS 2020 Guilin Li, Junlei Zhang, Yunhe Wang, Chuanjian Liu, Matthias Tan, Yunfeng Lin, Wei zhang, Jiashi Feng, Tong Zhang

In particular, we propose a novel joint-training framework to train plain CNN by leveraging the gradients of the ResNet counterpart.

Decentralized Accelerated Proximal Gradient Descent

no code implementations NeurIPS 2020 Haishan Ye, Ziang Zhou, Luo Luo, Tong Zhang

In this paper, we propose a new method which establishes the optimal computational complexity and a near optimal communication complexity.

How to Characterize The Landscape of Overparameterized Convolutional Neural Networks

1 code implementation NeurIPS 2020 Yihong Gu, Weizhong Zhang, Cong Fang, Jason D. Lee, Tong Zhang

With the help of a new technique called {\it neural network grafting}, we demonstrate that even during the entire training process, feature distributions of differently initialized networks remain similar at each layer.

Model Rubik’s Cube: Twisting Resolution, Depth and Width for TinyNets

2 code implementations NeurIPS 2020 Kai Han, Yunhe Wang, Qiulin Zhang, Wei zhang, Chunjing Xu, Tong Zhang

To this end, we summarize a tiny formula for downsizing neural architectures through a series of smaller models derived from the EfficientNet-B0 with the FLOPs constraint.

Image Classification

Model Rubik's Cube: Twisting Resolution, Depth and Width for TinyNets

5 code implementations28 Oct 2020 Kai Han, Yunhe Wang, Qiulin Zhang, Wei zhang, Chunjing Xu, Tong Zhang

To this end, we summarize a tiny formula for downsizing neural architectures through a series of smaller models derived from the EfficientNet-B0 with the FLOPs constraint.

Image Classification

Improving Constituency Parsing with Span Attention

1 code implementation Findings of the Association for Computational Linguistics 2020 Yuanhe Tian, Yan Song, Fei Xia, Tong Zhang

Constituency parsing is a fundamental and important task for natural language understanding, where a good representation of contextual information can help this task.

Constituency Parsing Natural Language Understanding

DiffMG: Differentiable Meta Graph Search for Heterogeneous Graph Neural Networks

1 code implementation7 Oct 2020 Yuhui Ding, Quanming Yao, Huan Zhao, Tong Zhang

Specifically, we search for a meta graph, which can capture more complex semantic relations than a meta path, to determine how graph neural networks (GNNs) propagate messages along different types of edges.

Neural Architecture Search Recommendation Systems

Disentangled Generative Causal Representation Learning

1 code implementation6 Oct 2020 Xinwei Shen, Furui Liu, Hanze Dong, Qing Lian, Zhitang Chen, Tong Zhang

This paper proposes a Disentangled gEnerative cAusal Representation (DEAR) learning method.


CorrAttack: Black-box Adversarial Attack with Structured Search

no code implementations3 Oct 2020 Zhichao Huang, Yaowei Huang, Tong Zhang

We show that searching over the structured space can be approximated by a time-varying contextual bandits problem, where the attacker takes feature of the associated arm to make modifications of the input, and receives an immediate reward as the reduction of the loss function.

Adversarial Attack Multi-Armed Bandits

Interest-Behaviour Multiplicative Network for Resource-limited Recommendation

no code implementations24 Sep 2020 Qianliang Wu, Tong Zhang, Zhen Cui, Jian Yang

In this paper, we aim to mine the cue of user preferences in resource-limited recommendation tasks, for which purpose we specifically build a large used car transaction dataset possessing resource-limitation characteristics.

Instance-Aware Graph Convolutional Network for Multi-Label Classification

no code implementations19 Aug 2020 Yun Wang, Tong Zhang, Zhen Cui, Chunyan Xu, Jian Yang

For label diffusion of instance-awareness in graph convolution, rather than using the statistical label correlation alone, an image-dependent label correlation matrix (LCM), fusing both the statistical LCM and an individual one of each image instance, is constructed for graph inference on labels to inject adaptive information of label-awareness into the learned features of the model.

Classification General Classification +2

Graph Wasserstein Correlation Analysis for Movie Retrieval

no code implementations ECCV 2020 Xueya Zhang, Tong Zhang, Xiaobin Hong, Zhen Cui, Jian Yang

Spectral graph filtering is introduced to encode graph signals, which are then embedded as probability distributions in a Wasserstein space, called graph Wasserstein metric learning.

Metric Learning

Towards Purely Unsupervised Disentanglement of Appearance and Shape for Person Images Generation

no code implementations26 Jul 2020 Hongtao Yang, Tong Zhang, Wenbing Huang, Xuming He, Fatih Porikli

To be clear, in this paper, we refer unsupervised learning as learning without task-specific human annotations, pairs or any form of weak supervision.)


Modeling from Features: a Mean-field Framework for Over-parameterized Deep Neural Networks

no code implementations3 Jul 2020 Cong Fang, Jason D. Lee, Pengkun Yang, Tong Zhang

This new representation overcomes the degenerate situation where all the hidden units essentially have only one meaningful hidden unit in each middle layer, and further leads to a simpler representation of DNNs, for which the training objective can be reformulated as a convex optimization problem via suitable re-parameterization.

Joint Chinese Word Segmentation and Part-of-speech Tagging via Two-way Attentions of Auto-analyzed Knowledge

1 code implementation ACL 2020 Yuanhe Tian, Yan Song, Xiang Ao, Fei Xia, Xiaojun Quan, Tong Zhang, Yonggang Wang

Chinese word segmentation (CWS) and part-of-speech (POS) tagging are important fundamental tasks for Chinese language processing, where joint learning of them is an effective one-step solution for both tasks.

Chinese Word Segmentation Part-Of-Speech Tagging +1

Guided Learning of Nonconvex Models through Successive Functional Gradient Optimization

no code implementations ICML 2020 Rie Johnson, Tong Zhang

This paper presents a framework of successive functional gradient optimization for training nonconvex models such as neural networks, where training is driven by mirror descent in a function space.

Picasso: A Sparse Learning Library for High Dimensional Data Analysis in R and Python

1 code implementation27 Jun 2020 Jason Ge, Xingguo Li, Haoming Jiang, Han Liu, Tong Zhang, Mengdi Wang, Tuo Zhao

We describe a new library named picasso, which implements a unified framework of pathwise coordinate optimization for a variety of sparse learning problems (e. g., sparse linear regression, sparse logistic regression, sparse Poisson regression and scaled sparse linear regression) combined with efficient active set selection strategies.

Sparse Learning

End-to-end Learning for Inter-Vehicle Distance and Relative Velocity Estimation in ADAS with a Monocular Camera

1 code implementation7 Jun 2020 Zhenbo Song, Jianfeng Lu, Tong Zhang, Hongdong Li

In this paper, we propose a monocular camera-based inter-vehicle distance and relative velocity estimation method based on end-to-end training of a deep neural network.

Optical Flow Estimation

Synthetic Learning: Learn From Distributed Asynchronized Discriminator GAN Without Sharing Medical Image Data

1 code implementation CVPR 2020 Qi Chang, Hui Qu, Yikai Zhang, Mert Sabuncu, Chao Chen, Tong Zhang, Dimitris Metaxas

In this paper, we propose a data privacy-preserving and communication efficient distributed GAN learning framework named Distributed Asynchronized Discriminator GAN (AsynDGAN).

Multi-consensus Decentralized Accelerated Gradient Descent

no code implementations2 May 2020 Haishan Ye, Luo Luo, Ziang Zhou, Tong Zhang

We propose a novel algorithm that can achieve near optimal communication complexity, matching the known lower bound up to a logarithmic factor of the condition number of the problem.

NetML: A Challenge for Network Traffic Analytics

1 code implementation25 Apr 2020 Onur Barut, Yan Luo, Tong Zhang, Weigang Li, Peilong Li

Classifying network traffic is the basis for important network applications.

Malware Detection

Keyphrase Generation with Cross-Document Attention

no code implementations21 Apr 2020 Shizhe Diao, Yan Song, Tong Zhang

Keyphrase generation aims to produce a set of phrases summarizing the essentials of a given document.

Keyphrase Generation

MiLeNAS: Efficient Neural Architecture Search via Mixed-Level Reformulation

1 code implementation CVPR 2020 Chaoyang He, Haishan Ye, Li Shen, Tong Zhang

To remedy this, this paper proposes \mldas, a mixed-level reformulation for NAS that can be optimized efficiently and reliably.

Bilevel Optimization Neural Architecture Search +1

Attention-guided Chained Context Aggregation for Semantic Segmentation

3 code implementations27 Feb 2020 Quan Tang, Fagui Liu, Tong Zhang, Jun Jiang, Yu Zhang

The way features propagate in Fully Convolutional Networks is of momentous importance to capture multi-scale contexts for obtaining precise segmentation masks.

Semantic Segmentation

Bidirectional Generative Modeling Using Adversarial Gradient Estimation

2 code implementations21 Feb 2020 Xinwei Shen, Tong Zhang, Kani Chen

This paper considers the general $f$-divergence formulation of bidirectional generative modeling, which includes VAE and BiGAN as special cases.

A Generalized Neural Tangent Kernel Analysis for Two-layer Neural Networks

no code implementations NeurIPS 2020 Zixiang Chen, Yuan Cao, Quanquan Gu, Tong Zhang

In this paper, we provide a generalized neural tangent kernel analysis and show that noisy gradient descent with weight decay can still exhibit a "kernel-like" behavior.

Learning Theory

Graph Inference Learning for Semi-supervised Classification

no code implementations ICLR 2020 Chunyan Xu, Zhen Cui, Xiaobin Hong, Tong Zhang, Jian Yang, Wei Liu

In this work, we address semi-supervised classification of graph data, where the categories of those unlabeled nodes are inferred from labeled nodes as well as graph structures.

Classification General Classification +1

Accelerated Dual-Averaging Primal-Dual Method for Composite Convex Minimization

no code implementations15 Jan 2020 Conghui Tan, Yuqiu Qian, Shiqian Ma, Tong Zhang

Dual averaging-type methods are widely used in industrial machine learning applications due to their ability to promoting solution structure (e. g., sparsity) efficiently.

Stochastic Recursive Gradient Descent Ascent for Stochastic Nonconvex-Strongly-Concave Minimax Problems

no code implementations NeurIPS 2020 Luo Luo, Haishan Ye, Zhichao Huang, Tong Zhang

We consider nonconvex-concave minimax optimization problems of the form $\min_{\bf x}\max_{\bf y\in{\mathcal Y}} f({\bf x},{\bf y})$, where $f$ is strongly-concave in $\bf y$ but possibly nonconvex in $\bf x$ and ${\mathcal Y}$ is a convex and compact set.

LTP: A New Active Learning Strategy for CRF-Based Named Entity Recognition

1 code implementation8 Jan 2020 Mingyi Liu, Zhiying Tu, Tong Zhang, Tonghua Su, Zhongjie Wang

In this paper, we first examine traditional active learning strategies in a specific case of BiLstm-CRF that has widely used in named entity recognition on several typical datasets.

Active Learning Named Entity Recognition +2

Fast Generalized Matrix Regression with Applications in Machine Learning

no code implementations27 Dec 2019 Haishan Ye, Shusen Wang, Zhihua Zhang, Tong Zhang

Fast matrix algorithms have become the fundamental tools of machine learning in big data era.

Divergence-Augmented Policy Optimization

1 code implementation NeurIPS 2019 Qing Wang, Yingru Li, Jiechao Xiong, Tong Zhang

In deep reinforcement learning, policy optimization methods need to deal with issues such as function approximation and the reuse of off-policy data.

Atari Games Policy Gradient Methods +1

Dual-Attention Graph Convolutional Network

no code implementations28 Nov 2019 Xueya Zhang, Tong Zhang, Wenting Zhao, Zhen Cui, Jian Yang

Graph convolutional networks (GCNs) have shown the powerful ability in text structure representation and effectively facilitate the task of text classification.

Text Classification

Stable Learning via Sample Reweighting

no code implementations28 Nov 2019 Zheyan Shen, Peng Cui, Tong Zhang, Kun Kuang

We consider the problem of learning linear prediction models with model misspecification bias.

Variable Selection

Bridging the Gap between Sample-based and One-shot Neural Architecture Search with BONAS

1 code implementation NeurIPS 2020 Han Shi, Renjie Pi, Hang Xu, Zhenguo Li, James T. Kwok, Tong Zhang

In this work, we propose BONAS (Bayesian Optimized Neural Architecture Search), a sample-based NAS framework which is accelerated using weight-sharing to evaluate multiple related architectures simultaneously.

Neural Architecture Search

A Fast Sampling Gradient Tree Boosting Framework

no code implementations20 Nov 2019 Daniel Chao Zhou, Zhongming Jin, Tong Zhang

As an adaptive, interpretable, robust, and accurate meta-algorithm for arbitrary differentiable loss functions, gradient tree boosting is one of the most popular machine learning techniques, though the computational expensiveness severely limits its usage.

Convex Formulation of Overparameterized Deep Neural Networks

no code implementations18 Nov 2019 Cong Fang, Yihong Gu, Weizhong Zhang, Tong Zhang

This new analysis is consistent with empirical observations that deep neural networks are capable of learning efficient feature representations.

Sparse Coding on Cascaded Residuals

no code implementations7 Nov 2019 Tong Zhang, Fatih Porikli

The residual at a layer is computed by the difference between the aggregated reconstructions of the previous layers and the downsampled original image at that layer.

Denoising Dictionary Learning

Spatial Sparse subspace clustering for Compressive Spectral imaging

no code implementations5 Nov 2019 Jianchen Zhu, Tong Zhang, Shengjie Zhao, Carlos Hinojosa, Zengli Liu, Gonzalo R. Arce

This paper aims at developing a clustering approach with spectral images directly from CASSI compressive measurements.

Image Clustering

Over Parameterized Two-level Neural Networks Can Learn Near Optimal Feature Representations

no code implementations25 Oct 2019 Cong Fang, Hanze Dong, Tong Zhang

Recently, over-parameterized neural networks have been extensively analyzed in the literature.

Mirror Natural Evolution Strategies

no code implementations25 Oct 2019 Haishan Ye, Tong Zhang

We show that the estimated covariance matrix of MiNES converges to the inverse of Hessian matrix of the objective function with a sublinear convergence rate.

A Stochastic Extra-Step Quasi-Newton Method for Nonsmooth Nonconvex Optimization

no code implementations21 Oct 2019 Ming-Han Yang, Andre Milzarek, Zaiwen Wen, Tong Zhang

In this paper, a novel stochastic extra-step quasi-Newton method is developed to solve a class of nonsmooth nonconvex composite optimization problems.

Hierarchical Neural Architecture Search via Operator Clustering

1 code implementation26 Sep 2019 Guilin Li, Xing Zhang, Zitong Wang, Matthias Tan, Jiashi Feng, Zhenguo Li, Tong Zhang

Recently, the efficiency of automatic neural architecture design has been significantly improved by gradient-based search methods such as DARTS.

Neural Architecture Search

Multi-objective Neural Architecture Search via Predictive Network Performance Optimization

no code implementations25 Sep 2019 Han Shi, Renjie Pi, Hang Xu, Zhenguo Li, James T. Kwok, Tong Zhang

Inspired by the nature of the graph structure of a neural network, we propose BOGCN-NAS, a NAS algorithm using Bayesian Optimization with Graph Convolutional Network (GCN) predictor.

Neural Architecture Search

Self-supervised Recurrent Neural Network for 4D Abdominal and In-utero MR Imaging

no code implementations28 Aug 2019 Tong Zhang, Laurence H. Jackson, Alena Uus, James R. Clough, Lisa Story, Mary A. Rutherford, Joseph V. Hajnal, Maria Deprez

The results show that the proposed pipeline can accurately estimate the respiratory state and reconstruct 4D SR volumes with better or similar performance to the 3D SVR pipeline with less than 20\% sparsely selected slices.

Image Reconstruction Motion Estimation +1

$\texttt{DeepSqueeze}$: Decentralization Meets Error-Compensated Compression

no code implementations17 Jul 2019 Hanlin Tang, Xiangru Lian, Shuang Qiu, Lei Yuan, Ce Zhang, Tong Zhang, Ji Liu

Since the \emph{decentralized} training has been witnessed to be superior to the traditional \emph{centralized} training in the communication restricted scenario, therefore a natural question to ask is "how to apply the error-compensated technology to the decentralized learning to further reduce the communication cost."

Optimal Feature Transport for Cross-View Image Geo-Localization

1 code implementation11 Jul 2019 Yujiao Shi, Xin Yu, Liu Liu, Tong Zhang, Hongdong Li

This paper proposes a novel Cross-View Feature Transport (CVFT) technique to explicitly establish cross-view domain transfer that facilitates feature alignment between ground and aerial images.

Image-Based Localization Metric Learning

Reinforced Training Data Selection for Domain Adaptation

1 code implementation ACL 2019 Miaofeng Liu, Yan Song, Hongbin Zou, Tong Zhang

Supervised models suffer from the problem of domain shifting where distribution mismatch in the data across domains greatly affect model performance.

Dependency Parsing Domain Adaptation +2

Estimating and Inferring the Maximum Degree of Stimulus-Locked Time-Varying Brain Connectivity Networks

no code implementations28 May 2019 Kean Ming Tan, Junwei Lu, Tong Zhang, Han Liu

To address this issue, neuroscientists have been measuring brain activity under natural viewing experiments in which the subjects are given continuous stimuli, such as watching a movie or listening to a story.

Experimental Design

DoubleSqueeze: Parallel Stochastic Gradient Descent with Double-Pass Error-Compensated Compression

no code implementations15 May 2019 Hanlin Tang, Xiangru Lian, Chen Yu, Tong Zhang, Ji Liu

For example, under the popular parameter server model for distributed learning, the worker nodes need to send the compressed local gradients to the parameter server, which performs the aggregation.

MAP Inference via L2-Sphere Linear Program Reformulation

1 code implementation9 May 2019 Baoyuan Wu, Li Shen, Tong Zhang, Bernard Ghanem

Thus, LS-LP is equivalent to the original MAP inference problem.

DHER: Hindsight Experience Replay for Dynamic Goals

1 code implementation ICLR 2019 Meng Fang, Cheng Zhou, Bei Shi, Boqing Gong, Jia Xu, Tong Zhang

Dealing with sparse rewards is one of the most important challenges in reinforcement learning (RL), especially when a goal is dynamic (e. g., to grasp a moving object).

Object Tracking

NATTACK: Learning the Distributions of Adversarial Examples for an Improved Black-Box Attack on Deep Neural Networks

1 code implementation1 May 2019 Yandong Li, Lijun Li, Liqiang Wang, Tong Zhang, Boqing Gong

Powerful adversarial attack methods are vital for understanding how to construct robust deep neural networks (DNNs) and for thoroughly testing defense techniques.

Adversarial Attack

Neural Collaborative Subspace Clustering

no code implementations24 Apr 2019 Tong Zhang, Pan Ji, Mehrtash Harandi, Wenbing Huang, Hongdong Li

We introduce the Neural Collaborative Subspace Clustering, a neural model that discovers clusters of data points drawn from a union of low-dimensional subspaces.

Efficient Decision-based Black-box Adversarial Attacks on Face Recognition

no code implementations CVPR 2019 Yinpeng Dong, Hang Su, Baoyuan Wu, Zhifeng Li, Wei Liu, Tong Zhang, Jun Zhu

In this paper, we evaluate the robustness of state-of-the-art face recognition models in the decision-based black-box attack setting, where the attackers have no access to the model parameters and gradients, but can only acquire hard-label predictions by sending queries to the target model.

Face Recognition

Dynamic Layer Aggregation for Neural Machine Translation with Routing-by-Agreement

no code implementations15 Feb 2019 Zi-Yi Dou, Zhaopeng Tu, Xing Wang, Long-Yue Wang, Shuming Shi, Tong Zhang

With the promising progress of deep neural networks, layer aggregation has been used to fuse information across layers in various fields, such as computer vision and machine translation.

Machine Translation Translation

Sharp Analysis for Nonconvex SGD Escaping from Saddle Points

no code implementations1 Feb 2019 Cong Fang, Zhouchen Lin, Tong Zhang

In this paper, we give a sharp analysis for Stochastic Gradient Descent (SGD) and prove that SGD is able to efficiently escape from saddle points and find an $(\epsilon, O(\epsilon^{0. 5}))$-approximate second-order stationary point in $\tilde{O}(\epsilon^{-3. 5})$ stochastic gradient computations for generic nonconvex optimization problems, when the objective function satisfies gradient-Lipschitz, Hessian-Lipschitz, and dispersive noise assumptions.

Stochastic Optimization

Tencent ML-Images: A Large-Scale Multi-Label Image Database for Visual Representation Learning

1 code implementation7 Jan 2019 Baoyuan Wu, Weidong Chen, Yanbo Fan, Yong Zhang, Jinlong Hou, Jie Liu, Tong Zhang

In this work, we propose to train CNNs from images annotated with multiple tags, to enhance the quality of visual representation of the trained CNN model.

Image Classification Object Detection +4

Cross-Database Micro-Expression Recognition: A Benchmark

no code implementations19 Dec 2018 Yuan Zong, Tong Zhang, Wenming Zheng, Xiaopeng Hong, Chuangao Tang, Zhen Cui, Guoying Zhao

Cross-database micro-expression recognition (CDMER) is one of recently emerging and interesting problem in micro-expression analysis.

Domain Adaptation Micro-Expression Recognition

Finite-Sample Analysis For Decentralized Batch Multi-Agent Reinforcement Learning With Networked Agents

no code implementations6 Dec 2018 Kaiqing Zhang, Zhuoran Yang, Han Liu, Tong Zhang, Tamer Başar

This work appears to be the first finite-sample analysis for batch MARL, a step towards rigorous theoretical understanding of general MARL algorithms in the finite-sample regime.

Multi-agent Reinforcement Learning reinforcement-learning

Stochastic Expectation Maximization with Variance Reduction

no code implementations NeurIPS 2018 Jianfei Chen, Jun Zhu, Yee Whye Teh, Tong Zhang

However, sEM has a slower asymptotic convergence rate than batch EM, and requires a decreasing sequence of step sizes, which is difficult to tune.

Stochastic Primal-Dual Method for Empirical Risk Minimization with O(1) Per-Iteration Complexity

no code implementations NeurIPS 2018 Conghui Tan, Tong Zhang, Shiqian Ma, Ji Liu

Regularized empirical risk minimization problem with linear predictor appears frequently in machine learning.

SPIDER: Near-Optimal Non-Convex Optimization via Stochastic Path-Integrated Differential Estimator

no code implementations NeurIPS 2018 Cong Fang, Chris Junchi Li, Zhouchen Lin, Tong Zhang

Specially, we prove that the SPIDER-SFO algorithm achieves a gradient computation cost of $\mathcal{O}\left( \min( n^{1/2} \epsilon^{-2}, \epsilon^{-3} ) \right)$ to find an $\epsilon$-approximate first-order stationary point.

Stochastic Optimization

Cross-database non-frontal facial expression recognition based on transductive deep transfer learning

no code implementations30 Nov 2018 Keyu Yan, Wenming Zheng, Tong Zhang, Yuan Zong, Zhen Cui

Cross-database non-frontal expression recognition is a very meaningful but rather difficult subject in the fields of computer vision and affect computing.

Facial Expression Recognition Transfer Learning

Neural Machine Translation with Adequacy-Oriented Learning

no code implementations21 Nov 2018 Xiang Kong, Zhaopeng Tu, Shuming Shi, Eduard Hovy, Tong Zhang

Although Neural Machine Translation (NMT) models have advanced state-of-the-art performance in machine translation, they face problems like the inadequate translation.

Machine Translation Translation

Super-Identity Convolutional Neural Network for Face Hallucination

no code implementations ECCV 2018 Kaipeng Zhang, Zhanpeng Zhang, Chia-Wen Cheng, Winston H. Hsu, Yu Qiao, Wei Liu, Tong Zhang

Face hallucination is a generative task to super-resolve the facial image with low resolution while human perception of face heavily relies on identity information.

14 Face Generation +1

Scalable Deep $k$-Subspace Clustering

no code implementations2 Nov 2018 Tong Zhang, Pan Ji, Mehrtash Harandi, Richard Hartley, Ian Reid

In this paper, we introduce a method that simultaneously learns an embedding space along subspaces within it to minimize a notion of reconstruction error, thus addressing the problem of subspace clustering in an end-to-end learning paradigm.

Multi-Head Attention with Disagreement Regularization

no code implementations EMNLP 2018 Jian Li, Zhaopeng Tu, Baosong Yang, Michael R. Lyu, Tong Zhang

Multi-head attention is appealing for the ability to jointly attend to information from different representation subspaces at different positions.


Exploiting Deep Representations for Neural Machine Translation

no code implementations EMNLP 2018 Zi-Yi Dou, Zhaopeng Tu, Xing Wang, Shuming Shi, Tong Zhang

Advanced neural machine translation (NMT) models generally implement encoder and decoder as multiple layers, which allows systems to model complex functions and capture complicated linguistic structures.

Machine Translation Translation

Orthogonal Deep Features Decomposition for Age-Invariant Face Recognition

no code implementations ECCV 2018 Yitong Wang, Dihong Gong, Zheng Zhou, Xing Ji, Hao Wang, Zhifeng Li, Wei Liu, Tong Zhang

Extensive experiments conducted on the three public domain face aging datasets (MORPH Album 2, CACD-VS and FG-NET) have shown the effectiveness of the proposed approach and the value of the constructed CAF dataset on AIFR.

Age-Invariant Face Recognition

Parametrized Deep Q-Networks Learning: Reinforcement Learning with Discrete-Continuous Hybrid Action Space

3 code implementations10 Oct 2018 Jiechao Xiong, Qing Wang, Zhuoran Yang, Peng Sun, Lei Han, Yang Zheng, Haobo Fu, Tong Zhang, Ji Liu, Han Liu

Most existing deep reinforcement learning (DRL) frameworks consider either discrete action space or continuous action space solely.



no code implementations27 Sep 2018 Miaofeng Liu, Yan Song, Hongbin Zou, Tong Zhang

Following the TDS methodology, in this paper, we propose a general data selection framework with representation learning and distribution matching simultaneously for domain adaptation on neural models.

Dependency Parsing Domain Adaptation +3

Fully Implicit Online Learning

no code implementations25 Sep 2018 Chaobing Song, Ji Liu, Han Liu, Yong Jiang, Tong Zhang

Regularized online learning is widely used in machine learning applications.

online learning

TStarBots: Defeating the Cheating Level Builtin AI in StarCraft II in the Full Game

3 code implementations19 Sep 2018 Peng Sun, Xinghai Sun, Lei Han, Jiechao Xiong, Qing Wang, Bo Li, Yang Zheng, Ji Liu, Yongsheng Liu, Han Liu, Tong Zhang

Both TStarBot1 and TStarBot2 are able to defeat the built-in AI agents from level 1 to level 10 in a full game (1v1 Zerg-vs-Zerg game on the AbyssalReef map), noting that level 8, level 9, and level 10 are cheating agents with unfair advantages such as full vision on the whole map and resource harvest boosting.

Decision Making Starcraft +1

A convex formulation for high-dimensional sparse sliced inverse regression

no code implementations17 Sep 2018 Kean Ming Tan, Zhaoran Wang, Tong Zhang, Han Liu, R. Dennis Cook

Sliced inverse regression is a popular tool for sufficient dimension reduction, which replaces covariates with a minimal set of their linear combinations without loss of information on the conditional distribution of the response given the covariates.

Dimensionality Reduction Variable Selection

Diffusion Approximations for Online Principal Component Estimation and Global Convergence

no code implementations NeurIPS 2017 Chris Junchi Li, Mengdi Wang, Han Liu, Tong Zhang

In this paper, we propose to adopt the diffusion approximation tools to study the dynamics of Oja's iteration which is an online stochastic gradient descent method for the principal component analysis.

End-to-end Active Object Tracking and Its Real-world Deployment via Reinforcement Learning

no code implementations10 Aug 2018 Wenhan Luo, Peng Sun, Fangwei Zhong, Wei Liu, Tong Zhang, Yizhou Wang

We further propose an environment augmentation technique and a customized reward function, which are crucial for successful training.

Frame Object Tracking +1

Video Re-localization

1 code implementation ECCV 2018 Yang Feng, Lin Ma, Wei Liu, Tong Zhang, Jiebo Luo

We first exploit and reorganize the videos in ActivityNet to form a new dataset for video re-localization research, which consists of about 10, 000 videos of diverse visual appearances associated with localized boundary information.

Copy Detection

Recurrent Fusion Network for Image Captioning

no code implementations ECCV 2018 Wenhao Jiang, Lin Ma, Yu-Gang Jiang, Wei Liu, Tong Zhang

In this paper, in order to exploit the complementary information from multiple encoders, we propose a novel Recurrent Fusion Network (RFNet) for tackling image captioning.

Image Captioning

Unsupervised Image-to-Image Translation with Stacked Cycle-Consistent Adversarial Networks

no code implementations ECCV 2018 Minjun Li, Hao-Zhi Huang, Lin Ma, Wei Liu, Tong Zhang, Yu-Gang Jiang

Recent studies on unsupervised image-to-image translation have made a remarkable progress by training a pair of generative adversarial networks with a cycle-consistent loss.

Translation Unsupervised Image-To-Image Translation

When Work Matters: Transforming Classical Network Structures to Graph CNN

no code implementations7 Jul 2018 Wenting Zhao, Chunyan Xu, Zhen Cui, Tong Zhang, Jiatao Jiang, Zhen-Yu Zhang, Jian Yang

In this paper, we aim to give a comprehensive analysis of when work matters by transforming different classical network structures to graph CNN, particularly in the basic graph recognition problem.

Graph Classification Video Understanding

SPIDER: Near-Optimal Non-Convex Optimization via Stochastic Path Integrated Differential Estimator

no code implementations NeurIPS 2018 Cong Fang, Chris Junchi Li, Zhouchen Lin, Tong Zhang

For stochastic first-order method, combining SPIDER with normalized gradient descent, we propose two new algorithms, namely SPIDER-SFO and SPIDER-SFO\textsuperscript{+}, that solve non-convex stochastic optimization problems using stochastic gradients only.

Stochastic Optimization

Graphical Nonconvex Optimization via an Adaptive Convex Relaxation

no code implementations ICML 2018 Qiang Sun, Kean Ming Tan, Han Liu, Tong Zhang

Our proposal is computationally tractable and produces an estimator that achieves the oracle rate of convergence.

Safe Element Screening for Submodular Function Minimization

no code implementations ICML 2018 Weizhong Zhang, Bin Hong, Lin Ma, Wei Liu, Tong Zhang

Relying on this study, we subsequently propose a novel safe screening method to quickly identify the elements guaranteed to be included (we refer to them as active) or excluded (inactive) in the final optimal solution of SFM during the optimization process.

Combinatorial Optimization Sparse Learning

An Algorithmic Framework of Variable Metric Over-Relaxed Hybrid Proximal Extra-Gradient Method

no code implementations ICML 2018 Li Shen, Peng Sun, Yitong Wang, Wei Liu, Tong Zhang

Specifically, we find that a large class of primal and primal-dual operator splitting algorithms are all special cases of VMOR-HPE.

Walk-Steered Convolution for Graph Classification

no code implementations16 Apr 2018 Jiatao Jiang, Chunyan Xu, Zhen Cui, Tong Zhang, Wenming Zheng, Jian Yang

As an analogy to a standard convolution kernel on image, Gaussian models implicitly coordinate those unordered vertices/nodes and edges in a local receptive field after projecting to the gradient space of Gaussian parameters.

Classification General Classification +2

Tensor graph convolutional neural network

no code implementations27 Mar 2018 Tong Zhang, Wenming Zheng, Zhen Cui, Yang Li

For cross graph convolution, a parameterized Kronecker sum operation is proposed to generate a conjunctive adjacency matrix characterizing the relationship between every pair of nodes across two subgraphs.

Matrix Completion

Communication Compression for Decentralized Training

no code implementations NeurIPS 2018 Hanlin Tang, Shaoduo Gan, Ce Zhang, Tong Zhang, Ji Liu

In this paper, We explore a natural question: {\em can the combination of both techniques lead to a system that is robust to both bandwidth and latency?}

Neural Stereoscopic Image Style Transfer

no code implementations ECCV 2018 Xinyu Gong, HaoZhi Huang, Lin Ma, Fumin Shen, Wei Liu, Tong Zhang

While each view of the stereoscopic pair is processed in an individual path, a novel feature aggregation strategy is proposed to effectively share information between the two paths.

Style Transfer

Fully Decentralized Multi-Agent Reinforcement Learning with Networked Agents

4 code implementations ICML 2018 Kaiqing Zhang, Zhuoran Yang, Han Liu, Tong Zhang, Tamer Başar

To this end, we propose two decentralized actor-critic algorithms with function approximation, which are applicable to large-scale MARL problems where both the number of states and the number of agents are massively large.

Multi-agent Reinforcement Learning reinforcement-learning