Search Results for author: Xiao Wang

Found 118 papers, 49 papers with code

Robust Sensible Adversarial Learning of Deep Neural Networks for Image Classification

1 code implementation20 May 2022 Jungeum Kim, Xiao Wang

Specifically, we define a sensible adversary which is useful for learning a robust model while keeping high natural accuracy.

Image Classification Object Recognition

Beyond Greedy Search: Tracking by Multi-Agent Reinforcement Learning-based Beam Search

no code implementations19 May 2022 Xiao Wang, Zhe Chen, Bo Jiang, Jin Tang, Bin Luo, DaCheng Tao

To track the target in a video, current visual trackers usually adopt greedy search for target object localization in each frame, that is, the candidate region with the maximum response score will be selected as the tracking result of each frame.

Decision Making Image Captioning +4

Image Gradient Decomposition for Parallel and Memory-Efficient Ptychographic Reconstruction

no code implementations12 May 2022 Xiao Wang, Aristeidis Tsaris, Debangshu Mukherjee, Mohamed Wahib, Peng Chen, Mark Oxley, Olga Ovchinnikova, Jacob Hinkle

In this paper, we propose a novel image gradient decomposition method that significantly reduces the memory footprint for ptychographic reconstruction by tessellating image gradients and diffraction measurements into tiles.

Accelerated Multiplicative Weights Update Avoids Saddle Points almost always

no code implementations25 Apr 2022 Yi Feng, Ioannis Panageas, Xiao Wang

We consider non-convex optimization problems with constraint that is a product of simplices.

On the Importance of Asymmetry for Siamese Representation Learning

1 code implementation CVPR 2022 Xiao Wang, Haoqi Fan, Yuandong Tian, Daisuke Kihara, Xinlei Chen

Many recent self-supervised frameworks for visual representation learning are based on certain forms of Siamese networks.

Representation Learning

Federated Class-Incremental Learning

1 code implementation CVPR 2022 Jiahua Dong, Lixu Wang, Zhen Fang, Gan Sun, Shichao Xu, Xiao Wang, Qi Zhu

It makes the global model suffer from significant catastrophic forgetting on old classes in real-world scenarios, where local clients often collect new classes continuously and have very limited storage memory to store old classes.

class-incremental learning Federated Learning +1

Unpaired Image Captioning by Image-level Weakly-Supervised Visual Concept Recognition

no code implementations7 Mar 2022 Peipei Zhu, Xiao Wang, Yong Luo, Zhenglong Sun, Wei-Shi Zheng, YaoWei Wang, Changwen Chen

The image-level labels are utilized to train a weakly-supervised object recognition model to extract object information (e. g., instance) in an image, and the extracted instances are adopted to infer the relationships among different objects based on an enhanced graph neural network (GNN).

Image Captioning Object Recognition

Space4HGNN: A Novel, Modularized and Reproducible Platform to Evaluate Heterogeneous Graph Neural Network

1 code implementation18 Feb 2022 Tianyu Zhao, Cheng Yang, Yibo Li, Quan Gan, Zhenyi Wang, Fengqi Liang, Huan Zhao, Yingxia Shao, Xiao Wang, Chuan Shi

Heterogeneous Graph Neural Network (HGNN) has been successfully employed in various tasks, but we cannot accurately know the importance of different design dimensions of HGNNs due to diverse architectures and applied scenarios.

Tiny Object Tracking: A Large-scale Dataset and A Baseline

1 code implementation11 Feb 2022 Yabin Zhu, Chenglong Li, Yao Liu, Xiao Wang, Jin Tang, Bin Luo, Zhixiang Huang

Tiny objects, frequently appearing in practical applications, have weak appearance and features, and receive increasing interests in meany vision tasks, such as object detection and segmentation.

Knowledge Distillation object-detection +2

Confidence May Cheat: Self-Training on Graph Neural Networks under Distribution Shift

no code implementations27 Jan 2022 Hongrui Liu, Binbin Hu, Xiao Wang, Chuan Shi, Zhiqiang Zhang, Jun Zhou

To this end, in this paper, we propose a novel Distribution Recovered Graph Self-Training framework (DR-GST), which could recover the distribution of the original labeled dataset.

Variational Inference

Event-based Video Reconstruction via Potential-assisted Spiking Neural Network

no code implementations CVPR 2022 Lin Zhu, Xiao Wang, Yi Chang, Jianing Li, Tiejun Huang, Yonghong Tian

We propose a novel Event-based Video reconstruction framework based on a fully Spiking Neural Network (EVSNN), which utilizes Leaky-Integrate-and-Fire (LIF) neuron and Membrane Potential (MP) neuron.

Image Reconstruction Video Reconstruction

Debiased Graph Neural Networks with Agnostic Label Selection Bias

no code implementations19 Jan 2022 Shaohua Fan, Xiao Wang, Chuan Shi, Kun Kuang, Nian Liu, Bai Wang

Then to remove the bias in GNN estimation, we propose a novel Debiased Graph Neural Networks (DGNN) with a differentiated decorrelation regularizer.

Selection bias

Compact Graph Structure Learning via Mutual Information Compression

1 code implementation14 Jan 2022 Nian Liu, Xiao Wang, Lingfei Wu, Yu Chen, Xiaojie Guo, Chuan Shi

Furthermore, we maintain the performance of estimated views and the final view and reduce the mutual information of every two views.

Graph structure learning

MutualFormer: Multi-Modality Representation Learning via Mutual Transformer

no code implementations2 Dec 2021 Xixi Wang, Bo Jiang, Xiao Wang, Bin Luo

In this work, we re-thinking the self-attention based Transformer and propose a novel MutualFormer for multi-modality data fusion and representation.

Representation Learning RGB-D Salient Object Detection +2

Universal Graph Convolutional Networks

1 code implementation NeurIPS 2021 Di Jin, Zhizhi Yu, Cuiying Huo, Rui Wang, Xiao Wang, Dongxiao He, Jiawei Han

So can we reasonably utilize these segmentation rules to design a universal propagation mechanism independent of the network structural assumption?

Generalizing Graph Neural Networks on Out-Of-Distribution Graphs

no code implementations20 Nov 2021 Shaohua Fan, Xiao Wang, Chuan Shi, Peng Cui, Bai Wang

Graph Neural Networks (GNNs) are proposed without considering the agnostic distribution shifts between training and testing graphs, inducing the degeneration of the generalization ability of GNNs on Out-Of-Distribution (OOD) settings.

Causal Inference

CoSeg: Cognitively Inspired Unsupervised Generic Event Segmentation

no code implementations30 Sep 2021 Xiao Wang, Jingen Liu, Tao Mei, Jiebo Luo

Unlike the mainstream clustering-based methods, our framework exploits a transformer-based feature reconstruction scheme to detect event boundary by reconstruction errors.

Boundary Detection Event Segmentation +1

Be Confident! Towards Trustworthy Graph Neural Networks via Confidence Calibration

2 code implementations NeurIPS 2021 Xiao Wang, Hongrui Liu, Chuan Shi, Cheng Yang

Specifically, we first verify that the confidence distribution in a graph has homophily property, and this finding inspires us to design a calibration GNN model (CaGCN) to learn the calibration function.

Inferential Wasserstein Generative Adversarial Networks

no code implementations13 Sep 2021 Yao Chen, Qingyi Gao, Xiao Wang

The Wasserstein GAN (WGAN) leverages the Wasserstein distance to avoid the caveats in the minmax two-player training of GANs but has other defects such as mode collapse and lack of metric to detect the convergence.

Constants of Motion: The Antidote to Chaos in Optimization and Game Dynamics

no code implementations8 Sep 2021 Georgios Piliouras, Xiao Wang

Several recent works in online optimization and game dynamics have established strong negative complexity results including the formal emergence of instability and chaos even in small such settings, e. g., $2\times 2$ games.

VisEvent: Reliable Object Tracking via Collaboration of Frame and Event Flows

2 code implementations11 Aug 2021 Xiao Wang, Jianing Li, Lin Zhu, Zhipeng Zhang, Zhe Chen, Xin Li, YaoWei Wang, Yonghong Tian, Feng Wu

Different from visible cameras which record intensity images frame by frame, the biologically inspired event camera produces a stream of asynchronous and sparse events with much lower latency.

Object Tracking

Learn to Match: Automatic Matching Network Design for Visual Tracking

1 code implementation ICCV 2021 Zhipeng Zhang, Yihao Liu, Xiao Wang, Bing Li, Weiming Hu

Siamese tracking has achieved groundbreaking performance in recent years, where the essence is the efficient matching operator cross-correlation and its variants.

Visual Tracking

MFGNet: Dynamic Modality-Aware Filter Generation for RGB-T Tracking

2 code implementations22 Jul 2021 Xiao Wang, Xiujun Shu, Shiliang Zhang, Bo Jiang, YaoWei Wang, Yonghong Tian, Feng Wu

The visible and thermal filters will be used to conduct a dynamic convolutional operation on their corresponding input feature maps respectively.

Rgb-T Tracking

Pseudo-Relevance Feedback for Multiple Representation Dense Retrieval

3 code implementations21 Jun 2021 Xiao Wang, Craig Macdonald, Nicola Tonellotto, Iadh Ounis

In particular, based on the pseudo-relevant set of documents identified using a first-pass dense retrieval, we extract representative feedback embeddings (using KMeans clustering) -- while ensuring that these embeddings discriminate among passages (based on IDF) -- which are then added to the query representation.

Information Retrieval Passage Ranking +1

Non-Transferable Learning: A New Approach for Model Ownership Verification and Applicability Authorization

1 code implementation ICLR 2022 Lixu Wang, Shichao Xu, Ruiqi Xu, Xiao Wang, Qi Zhu

Our NTL-based authorization approach instead provides data-centric protection, which we call applicability authorization, by significantly degrading the performance of the model on unauthorized data.

Tracking by Joint Local and Global Search: A Target-aware Attention based Approach

1 code implementation9 Jun 2021 Xiao Wang, Jin Tang, Bin Luo, YaoWei Wang, Yonghong Tian, Feng Wu

In this paper, we propose a novel and general target-aware attention mechanism (termed TANet) and integrate it with tracking-by-detection framework to conduct joint local and global search for robust tracking.

Object Tracking

Large-Scale Spatio-Temporal Person Re-identification: Algorithms and Benchmark

1 code implementation31 May 2021 Xiujun Shu, Xiao Wang, Xianghao Zang, Shiliang Zhang, Yuanqi Chen, Ge Li, Qi Tian

We also verified that models pre-trained on LaST can generalize well on existing datasets with short-term and cloth-changing scenarios.

Person Re-Identification

Guidance and Teaching Network for Video Salient Object Detection

no code implementations21 May 2021 Yingxia Jiao, Xiao Wang, Yu-Cheng Chou, Shouyuan Yang, Ge-Peng Ji, Rong Zhu, Ge Gao

Owing to the difficulties of mining spatial-temporal cues, the existing approaches for video salient object detection (VSOD) are limited in understanding complex and noisy scenarios, and often fail in inferring prominent objects.

object-detection Salient Object Detection +1

Self-supervised Heterogeneous Graph Neural Network with Co-contrastive Learning

3 code implementations19 May 2021 Xiao Wang, Nian Liu, Hui Han, Chuan Shi

Then the cross-view contrastive learning, as well as a view mask mechanism, is proposed, which is able to extract the positive and negative embeddings from two views.

Contrastive Learning

Substitutional Neural Image Compression

no code implementations16 May 2021 Xiao Wang, Wei Jiang, Wei Wang, Shan Liu, Brian Kulis, Peter Chin

The key idea is to replace the image to be compressed with a substitutional one that outperforms the original one in a desired way.

Image Compression

High-Robustness, Low-Transferability Fingerprinting of Neural Networks

no code implementations14 May 2021 Siyue Wang, Xiao Wang, Pin-Yu Chen, Pu Zhao, Xue Lin

This paper proposes Characteristic Examples for effectively fingerprinting deep neural networks, featuring high-robustness to the base model against model pruning as well as low-transferability to unassociated models.

Contrastive Learning with Stronger Augmentations

1 code implementation15 Apr 2021 Xiao Wang, Guo-Jun Qi

Thus, we propose a general framework called Contrastive Learning with Stronger Augmentations~(CLSA) to complement current contrastive learning approaches.

Contrastive Learning Representation Learning +2

Lorentzian Graph Convolutional Networks

no code implementations15 Apr 2021 Yiding Zhang, Xiao Wang, Chuan Shi, Nian Liu, Guojie Song

We also find that the performance of some hyperbolic GCNs can be improved by simply replacing the graph operations with those we defined in this paper.

Dynamic Attention guided Multi-Trajectory Analysis for Single Object Tracking

1 code implementation30 Mar 2021 Xiao Wang, Zhe Chen, Jin Tang, Bin Luo, YaoWei Wang, Yonghong Tian, Feng Wu

In this paper, we propose to introduce more dynamics by devising a dynamic attention-guided multi-trajectory tracking strategy.

Object Tracking

CaPC Learning: Confidential and Private Collaborative Learning

1 code implementation ICLR 2021 Christopher A. Choquette-Choo, Natalie Dullerud, Adam Dziedzic, Yunxiang Zhang, Somesh Jha, Nicolas Papernot, Xiao Wang

There is currently no method that enables machine learning in such a setting, where both confidentiality and privacy need to be preserved, to prevent both explicit and implicit sharing of data.

Fairness Federated Learning

Interpreting and Unifying Graph Neural Networks with An Optimization Framework

no code implementations28 Jan 2021 Meiqi Zhu, Xiao Wang, Chuan Shi, Houye Ji, Peng Cui

Graph Neural Networks (GNNs) have received considerable attention on graph-structured data learning for a wide variety of tasks.

Beyond Low-frequency Information in Graph Convolutional Networks

1 code implementation4 Jan 2021 Deyu Bo, Xiao Wang, Chuan Shi, HuaWei Shen

For a deeper understanding, we theoretically analyze the roles of low-frequency signals and high-frequency signals on learning node representations, which further explains why FAGCN can perform well on different types of networks.

NeuSpike-Net: High Speed Video Reconstruction via Bio-Inspired Neuromorphic Cameras

no code implementations ICCV 2021 Lin Zhu, Jianing Li, Xiao Wang, Tiejun Huang, Yonghong Tian

In this paper, we propose a NeuSpike-Net to learn both the high dynamic range and high motion sensitivity of DVS and the full texture sampling of spike camera to achieve high-speed and high dynamic image reconstruction.

Image Reconstruction Video Reconstruction

Deep Q Learning from Dynamic Demonstration with Behavioral Cloning

no code implementations1 Jan 2021 Xiaoshuang Li, Junchen Jin, Xiao Wang, Fei-Yue Wang

This study proposes a novel approach integrating deep Q learning from dynamic demonstrations with a behavioral cloning model (DQfDD-BC), which includes a supervised learning technique of instructing a DRL model to enhance its performance.

OpenAI Gym Q-Learning

A Survey on Heterogeneous Graph Embedding: Methods, Techniques, Applications and Sources

no code implementations30 Nov 2020 Xiao Wang, Deyu Bo, Chuan Shi, Shaohua Fan, Yanfang Ye, Philip S. Yu

Heterogeneous graphs (HGs) also known as heterogeneous information networks have become ubiquitous in real-world scenarios; therefore, HG embedding, which aims to learn representations in a lower-dimension space while preserving the heterogeneous structures and semantics for downstream tasks (e. g., node/graph classification, node clustering, link prediction), has drawn considerable attentions in recent years.

Graph Classification Graph Embedding +4

AdCo: Adversarial Contrast for Efficient Learning of Unsupervised Representations from Self-Trained Negative Adversaries

2 code implementations CVPR 2021 Qianjiang Hu, Xiao Wang, Wei Hu, Guo-Jun Qi

Contrastive learning relies on constructing a collection of negative examples that are sufficiently hard to discriminate against positive queries when their representations are self-trained.

Contrastive Learning

Cross-Lingual Document Retrieval with Smooth Learning

1 code implementation COLING 2020 Jiapeng Liu, Xiao Zhang, Dan Goldwasser, Xiao Wang

Cross-lingual document search is an information retrieval task in which the queries' language differs from the documents' language.

Information Retrieval

Dynamic Fusion based Federated Learning for COVID-19 Detection

no code implementations22 Sep 2020 Weishan Zhang, Tao Zhou, Qinghua Lu, Xiao Wang, Chunsheng Zhu, Haoyun Sun, Zhipeng Wang, Sin Kit Lo, Fei-Yue Wang

To improve communication efficiency and model performance, in this paper, we propose a novel dynamic fusion-based federated learning approach for medical diagnostic image analysis to detect COVID-19 infections.

Decision Making Federated Learning +2

Addressing Class Imbalance in Federated Learning

2 code implementations14 Aug 2020 Lixu Wang, Shichao Xu, Xiao Wang, Qi Zhu

Our experiments demonstrate the importance of acknowledging class imbalance and taking measures as early as possible in FL training, and the effectiveness of our method in mitigating the impact.

Federated Learning

Decision-making at Unsignalized Intersection for Autonomous Vehicles: Left-turn Maneuver with Deep Reinforcement Learning

no code implementations14 Aug 2020 Teng Liu, Xingyu Mu, Bing Huang, Xiaolin Tang, Fuqing Zhao, Xiao Wang, Dongpu Cao

Decision-making module enables autonomous vehicles to reach appropriate maneuvers in the complex urban environments, especially the intersection situations.

Autonomous Vehicles Decision Making +2

Deep Reinforced Query Reformulation for Information Retrieval

no code implementations15 Jul 2020 Xiao Wang, Craig Macdonald, Iadh Ounis

Query reformulations have long been a key mechanism to alleviate the vocabulary-mismatch problem in information retrieval, for example by expanding the queries with related query terms or by generating paraphrases of the queries.

Document Ranking Information Retrieval

STADB: A Self-Thresholding Attention Guided ADB Network for Person Re-identification

1 code implementation7 Jul 2020 Bo Jiang, Sheng Wang, Xiao Wang, Aihua Zheng

Specifically, STADB first obtains an attention map by channel-wise pooling and returns a drop mask by thresholding the attention map.

Person Re-Identification

AM-GCN: Adaptive Multi-channel Graph Convolutional Networks

no code implementations5 Jul 2020 Xiao Wang, Meiqi Zhu, Deyu Bo, Peng Cui, Chuan Shi, Jian Pei

We tackle the challenge and propose an adaptive multi-channel graph convolutional networks for semi-supervised classification (AM-GCN).

General Classification

Falsification-Based Robust Adversarial Reinforcement Learning

no code implementations1 Jul 2020 Xiao Wang, Saasha Nair, Matthias Althoff

Reinforcement learning (RL) has achieved tremendous progress in solving various sequential decision-making problems, e. g., control tasks in robotics.

Autonomous Vehicles Decision Making +1

Decorrelated Clustering with Data Selection Bias

1 code implementation29 Jun 2020 Xiao Wang, Shaohua Fan, Kun Kuang, Chuan Shi, Jiawei Liu, Bai Wang

Most of existing clustering algorithms are proposed without considering the selection bias in data.

Selection bias

Unbiased Contrastive Divergence Algorithm for Training Energy-Based Latent Variable Models

1 code implementation ICLR 2020 Yixuan Qiu, Lingsong Zhang, Xiao Wang

The contrastive divergence algorithm is a popular approach to training energy-based latent variable models, which has been widely used in many machine learning models such as the restricted Boltzmann machines and deep belief nets.

FMT:Fusing Multi-task Convolutional Neural Network for Person Search

no code implementations1 Mar 2020 Sulan Zhai, Shunqiang Liu, Xiao Wang, Jin Tang

Person search is to detect all persons and identify the query persons from detected persons in the image without proposals and bounding boxes, which is different from person re-identification.

Human Detection Person Re-Identification +2

Convergence to Second-Order Stationarity for Non-negative Matrix Factorization: Provably and Concurrently

no code implementations26 Feb 2020 Ioannis Panageas, Stratis Skoulakis, Antonios Varvitsiotis, Xiao Wang

Non-negative matrix factorization (NMF) is a fundamental non-convex optimization problem with numerous applications in Machine Learning (music analysis, document clustering, speech-source separation etc).

AdvMS: A Multi-source Multi-cost Defense Against Adversarial Attacks

no code implementations19 Feb 2020 Xiao Wang, Siyue Wang, Pin-Yu Chen, Xue Lin, Peter Chin

Designing effective defense against adversarial attacks is a crucial topic as deep neural networks have been proliferated rapidly in many security-critical domains such as malware detection and self-driving cars.

Malware Detection Self-Driving Cars

Block Switching: A Stochastic Approach for Deep Learning Security

no code implementations18 Feb 2020 Xiao Wang, Siyue Wang, Pin-Yu Chen, Xue Lin, Peter Chin

Recent study of adversarial attacks has revealed the vulnerability of modern deep learning models.

Last iterate convergence in no-regret learning: constrained min-max optimization for convex-concave landscapes

no code implementations17 Feb 2020 Qi Lei, Sai Ganesh Nagarajan, Ioannis Panageas, Xiao Wang

In a recent series of papers it has been established that variants of Gradient Descent/Ascent and Mirror Descent exhibit last iterate convergence in convex-concave zero-sum games.

online learning

Stochastic Approximate Gradient Descent via the Langevin Algorithm

no code implementations13 Feb 2020 Yixuan Qiu, Xiao Wang

We introduce a novel and efficient algorithm called the stochastic approximate gradient descent (SAGD), as an alternative to the stochastic gradient descent for cases where unbiased stochastic gradients cannot be trivially obtained.

Structural Deep Clustering Network

2 code implementations5 Feb 2020 Deyu Bo, Xiao Wang, Chuan Shi, Meiqi Zhu, Emiao Lu, Peng Cui

The strength of deep clustering methods is to extract the useful representations from the data itself, rather than the structure of data, which receives scarce attention in representation learning.

Deep Clustering Representation Learning

Physics-Based Iterative Reconstruction for Dual Source and Flying Focal Spot Computed Tomography

no code implementations26 Jan 2020 Xiao Wang, Robert D. MacDougall, Peng Chen, Charles A. Bouman, Simon K. Warfield

Our algorithm uses precise physics models to reconstruct from the native cone-beam geometry and interleaved dual source helical trajectory of a DS-FFS CT. To do so, we construct a noise physics model to represent data acquisition noise and a prior image model to represent image noise and texture.

Computed Tomography (CT)

\emph{cm}SalGAN: RGB-D Salient Object Detection with Cross-View Generative Adversarial Networks

1 code implementation21 Dec 2019 Bo Jiang, Zitai Zhou, Xiao Wang, Jin Tang, Bin Luo

Fusing complementary information of RGB and depth has been demonstrated to be effective for image salient object detection which is known as RGB-D salient object detection problem.

Computer Vision Edge Detection +5

Measuring Compositional Generalization: A Comprehensive Method on Realistic Data

2 code implementations ICLR 2020 Daniel Keysers, Nathanael Schärli, Nathan Scales, Hylke Buisman, Daniel Furrer, Sergii Kashubin, Nikola Momchev, Danila Sinopalnikov, Lukasz Stafiniak, Tibor Tihon, Dmitry Tsarkov, Xiao Wang, Marc van Zee, Olivier Bousquet

We present a large and realistic natural language question answering dataset that is constructed according to this method, and we use it to analyze the compositional generalization ability of three machine learning architectures.

Question Answering

Depth-Width Trade-offs for ReLU Networks via Sharkovsky's Theorem

no code implementations ICLR 2020 Vaggos Chatziafratis, Sai Ganesh Nagarajan, Ioannis Panageas, Xiao Wang

Motivated by our observation that the triangle waves used in Telgarsky's work contain points of period 3 - a period that is special in that it implies chaotic behavior based on the celebrated result by Li-Yorke - we proceed to give general lower bounds for the width needed to represent periodic functions as a function of the depth.

Hyperbolic Graph Attention Network

1 code implementation6 Dec 2019 Yiding Zhang, Xiao Wang, Xunqiang Jiang, Chuan Shi, Yanfang Ye

Graph neural network (GNN) has shown superior performance in dealing with graphs, which has attracted considerable research attention recently.

Graph Attention

Nanoconfined, dynamic electrolyte gating and memory effects in multilayered graphene-based membranes

no code implementations29 Nov 2019 Jing Xiao, Hualin Zhan, Zaiquan Xu, Xiao Wang, Ke Zhang, Zhiyuan Xiong, George P. Simon, Zhe Liu, Dan Li

Multilayered graphene-based nanoporous membranes with electrolyte incorporated between individual sheets is a unique nano-heterostructure system in which nanoconfined electrons in graphene and ions confined in between sheets are intimately coupled throughout the entire membrane.

Mesoscale and Nanoscale Physics Materials Science Soft Condensed Matter Applied Physics Chemical Physics

Independence Promoted Graph Disentangled Networks

no code implementations26 Nov 2019 Yanbei Liu, Xiao Wang, Shu Wu, Zhitao Xiao

In this paper, we propose a novel Independence Promoted Graph Disentangled Networks (IPGDN) to learn disentangled node representation while enhancing the independence among node representations.

Graph Classification Graph Clustering +1

Multi-Component Graph Convolutional Collaborative Filtering

1 code implementation25 Nov 2019 Xiao Wang, Ruijia Wang, Chuan Shi, Guojie Song, Qingyong Li

The interactions of users and items in recommender system could be naturally modeled as a user-item bipartite graph.

Collaborative Filtering Recommendation Systems

Eavesdrop the Composition Proportion of Training Labels in Federated Learning

no code implementations14 Oct 2019 Lixu Wang, Shichao Xu, Xiao Wang, Qi Zhu

Federated learning (FL) has recently emerged as a new form of collaborative machine learning, where a common model can be learned while keeping all the training data on local devices.

Federated Learning Inference Attack

ISTHMUS: Secure, Scalable, Real-time and Robust Machine Learning Platform for Healthcare

no code implementations29 Sep 2019 Akshay Arora, Arun Nethi, Priyanka Kharat, Vency Verghese, Grant Jenkins, Steve Miff, Vikas Chowdhry, Xiao Wang

There are multiple reasons why integrating ML models into healthcare has not been widely successful, but from a technical perspective, general-purpose commercial machine learning platforms are not a good fit for healthcare due to complexities in handling data quality issues, mandates to demonstrate clinical relevance, and a lack of ability to monitor performance in a highly regulated environment with stringent security and privacy needs.

Sensible adversarial learning

no code implementations25 Sep 2019 Jungeum Kim, Xiao Wang

The trade-off between robustness and standard accuracy has been consistently reported in the machine learning literature.

DG-GAN: the GAN with the duality gap

no code implementations25 Sep 2019 Cheng Peng, Hao Wang, Xiao Wang, Zhouwang Yang

Generative Adversarial Networks (GANs) are powerful, but difficult to understand and train because GANs is a min-max problem.

A Uniform Generalization Error Bound for Generative Adversarial Networks

no code implementations25 Sep 2019 Hao Chen, Zhanfeng Mo, Qingyi Gao, Zhouwang Yang, Xiao Wang

To better understand the unsupervised model, GANs, we establish the generalization bound, which uniformly holds with respect to the choice of generators.

Generalization Bounds

iWGAN: an Autoencoder WGAN for Inference

no code implementations25 Sep 2019 Yao Chen, Qingyi Gao, Xiao Wang

We further provide a rigorous probabilistic interpretation of our model under the framework of maximum likelihood estimation.

Deep Collaborative Filtering with Multi-Aspect Information in Heterogeneous Networks

no code implementations14 Sep 2019 Chuan Shi, Xiaotian Han, Li Song, Xiao Wang, Senzhang Wang, Junping Du, Philip S. Yu

However, the characteristics of users and the properties of items may stem from different aspects, e. g., the brand-aspect and category-aspect of items.

Collaborative Filtering Recommendation Systems

Temporal Network Embedding with Micro- and Macro-dynamics

1 code implementation10 Sep 2019 Yuanfu Lu, Xiao Wang, Chuan Shi, Philip S. Yu, Yanfang Ye

The micro-dynamics describe the formation process of network structures in a detailed manner, while the macro-dynamics refer to the evolution pattern of the network scale.

Network Embedding

Protecting Neural Networks with Hierarchical Random Switching: Towards Better Robustness-Accuracy Trade-off for Stochastic Defenses

1 code implementation20 Aug 2019 Xiao Wang, Siyue Wang, Pin-Yu Chen, Yanzhi Wang, Brian Kulis, Xue Lin, Peter Chin

However, one critical drawback of current defenses is that the robustness enhancement is at the cost of noticeable performance degradation on legitimate data, e. g., large drop in test accuracy.

Adversarial Robustness

Learning Target-oriented Dual Attention for Robust RGB-T Tracking

no code implementations12 Aug 2019 Rui Yang, Yabin Zhu, Xiao Wang, Chenglong Li, Jin Tang

RGB-Thermal object tracking attempt to locate target object using complementary visual and thermal infrared data.

Object Tracking Representation Learning +1

Deep Learning Models to Predict Pediatric Asthma Emergency Department Visits

no code implementations25 Jul 2019 Xiao Wang, Zhijie Wang, Yolande M. Pengetnze, Barry S. Lachman, Vikas Chowdhry

Pediatric asthma is the most prevalent chronic childhood illness, afflicting about 6. 2 million children in the United States.

Dense Feature Aggregation and Pruning for RGBT Tracking

no code implementations24 Jul 2019 Yabin Zhu, Chenglong Li, Bin Luo, Jin Tang, Xiao Wang

In different modalities, we propose to prune the densely aggregated features of all modalities in a collaborative way.

Learning Generalized Transformation Equivariant Representations via Autoencoding Transformations

no code implementations19 Jun 2019 Guo-Jun Qi, Liheng Zhang, Xiao Wang

Transformation Equivariant Representations (TERs) aim to capture the intrinsic visual structures that equivary to various transformations by expanding the notion of {\em translation} equivariance underlying the success of Convolutional Neural Networks (CNNs).

Translation

Improved Hard Example Mining by Discovering Attribute-based Hard Person Identity

no code implementations6 May 2019 Xiao Wang, Ziliang Chen, Rui Yang, Bin Luo, Jin Tang

In this paper, we propose Hard Person Identity Mining (HPIM) that attempts to refine the hard example mining to improve the exploration efficacy in person re-identification.

Metric Learning Person Re-Identification

Heterogeneous Graph Attention Network

2 code implementations WWW 2019 2019 Xiao Wang, Houye Ji, Chuan Shi, Bai Wang, Peng Cui, P. Yu, Yanfang Ye

With the learned importance from both node-level and semantic-level attention, the importance of node and meta-path can be fully considered.

Social and Information Networks

Pedestrian Attribute Recognition: A Survey

no code implementations22 Jan 2019 Xiao Wang, Shaofei Zheng, Rui Yang, Bin Luo, Jin Tang

We also review some popular network architectures which have widely applied in the deep learning community.

Computer Vision Multi-Label Learning +2

Quality-Aware Multimodal Saliency Detection via Deep Reinforcement Learning

no code implementations27 Nov 2018 Xiao Wang, Tao Sun, Rui Yang, Chenglong Li, Bin Luo, Jin Tang

In this paper, we propose an efficient quality-aware deep neural network to model the weight of data from each domain using deep reinforcement learning (DRL).

Decision Making object-detection +4

Describe and Attend to Track: Learning Natural Language guided Structural Representation and Visual Attention for Object Tracking

no code implementations25 Nov 2018 Xiao Wang, Chenglong Li, Rui Yang, Tianzhu Zhang, Jin Tang, Bin Luo

To refine the states of the target and re-track the target when it is back to view from heavy occlusion and out of view, we elaborately design a novel subnetwork to learn the target-driven visual attentions from the guidance of both visual and natural language cues.

Object Tracking

Most Probable Evolution Trajectories in a Genetic Regulatory System Excited by Stable Lévy Noise

no code implementations9 Oct 2018 Xiujun Cheng, Hui Wang, Xiao Wang, Jinqiao Duan, Xiaofan Li

We especially examine those most probable trajectories from low concentration state to high concentration state (i. e., the likely transcription regime) for certain parameters, in order to gain insights into the transcription processes and the tipping time for the transcription likely to occur.

Understanding Weight Normalized Deep Neural Networks with Rectified Linear Units

no code implementations NeurIPS 2018 Yixi Xu, Xiao Wang

This paper presents a general framework for norm-based capacity control for $L_{p, q}$ weight normalized deep neural networks.

Defensive Dropout for Hardening Deep Neural Networks under Adversarial Attacks

no code implementations13 Sep 2018 Siyue Wang, Xiao Wang, Pu Zhao, Wujie Wen, David Kaeli, Peter Chin, Xue Lin

Based on the observations of the effect of test dropout rate on test accuracy and attack success rate, we propose a defensive dropout algorithm to determine an optimal test dropout rate given the neural network model and the attacker's strategy for generating adversarial examples. We also investigate the mechanism behind the outstanding defense effects achieved by the proposed defensive dropout.

SINT++: Robust Visual Tracking via Adversarial Positive Instance Generation

no code implementations CVPR 2018 Xiao Wang, Chenglong Li, Bin Luo, Jin Tang

Based on the generated hard positive samples, we train a Siamese network for visual tracking and our experiments validate the effectiveness of the introduced algorithm.

Visual Tracking

Billion-scale Network Embedding with Iterative Random Projection

2 code implementations7 May 2018 Ziwei Zhang, Peng Cui, Haoyang Li, Xiao Wang, Wenwu Zhu

Network embedding, which learns low-dimensional vector representation for nodes in the network, has attracted considerable research attention recently.

Distributed Computing Link Prediction +2

Tracking Multiple Moving Objects Using Unscented Kalman Filtering Techniques

no code implementations5 Feb 2018 Xi Chen, Xiao Wang, Jianhua Xuan

Considering the ambiguity caused by the occlusion among multiple moving objects, we apply an unscented Kalman filtering (UKF) technique for reliable object detection and tracking.

Multiple Object Tracking object-detection +1

Structured Illumination in Spatial-Orientational Hyperspace

1 code implementation14 Dec 2017 Karl Zhanghao, Xingye Chen, Wenhui Liu, Meiqi Li, Chunyan Shan, Xiao Wang, Kun Zhao, Amit Lai, Hao Xie, Qionghai Dai, Peng Xi

The dipole nature of chromophore is important for both super-resolution microscopy and imaging molecular structure, which is nevertheless neglected in most microscopies, even including structured illumination microscopy (SIM) with polarized excitations.

Optics

Structural Deep Embedding for Hyper-Networks

1 code implementation28 Nov 2017 Ke Tu, Peng Cui, Xiao Wang, Fei Wang, Wenwu Zhu

These hyper-networks pose great challenges to existing network embedding methods when the hyperedges are indecomposable, that is to say, any subset of nodes in a hyperedge cannot form another hyperedge.

Social and Information Networks

TIMERS: Error-Bounded SVD Restart on Dynamic Networks

1 code implementation27 Nov 2017 Ziwei Zhang, Peng Cui, Jian Pei, Xiao Wang, Wenwu Zhu

By setting a maximum tolerated error as a threshold, we can trigger SVD restart automatically when the margin exceeds this threshold. We prove that the time complexity of our method is linear with respect to the number of local dynamic changes, and our method is general across different types of dynamic networks.

Social and Information Networks

A Survey on Network Embedding

no code implementations23 Nov 2017 Peng Cui, Xiao Wang, Jian Pei, Wenwu Zhu

Network embedding assigns nodes in a network to low-dimensional representations and effectively preserves the network structure.

Social and Information Networks

Deep Co-Space: Sample Mining Across Feature Transformation for Semi-Supervised Learning

no code implementations28 Jul 2017 Ziliang Chen, Keze Wang, Xiao Wang, Pai Peng, Ebroul Izquierdo, Liang Lin

Aiming at improving performance of visual classification in a cost-effective manner, this paper proposes an incremental semi-supervised learning paradigm called Deep Co-Space (DCS).

Classification General Classification +1

Detecting Drivable Area for Self-driving Cars: An Unsupervised Approach

no code implementations1 May 2017 Ziyi Liu, Siyu Yu, Xiao Wang, Nanning Zheng

Experiments show that our unsupervised approach is efficient and robust for detecting drivable area for self-driving cars.

Self-Driving Cars

On the Statistical Efficiency of Compositional Nonparametric Prediction

no code implementations6 Apr 2017 Yixi Xu, Jean Honorio, Xiao Wang

In this paper, we propose a compositional nonparametric method in which a model is expressed as a labeled binary tree of $2k+1$ nodes, where each node is either a summation, a multiplication, or the application of one of the $q$ basis functions to one of the $p$ covariates.

Font Size: Community Preserving Network Embedding

2 code implementations AAAI 2017 Xiao Wang, Peng Cui, Jing Wang, Jian Pei, Wenwu Zhu, Shiqiang Yang

While previous network embedding methods primarily preserve the microscopic structure, such as the first- and second-order proximities of nodes, the mesoscopic community structure, which is one of the most prominent feature of networks, is largely ignored.

Community Detection Network Embedding

Stochastic Quasi-Newton Methods for Nonconvex Stochastic Optimization

no code implementations5 Jul 2016 Xiao Wang, Shiqian Ma, Donald Goldfarb, Wei Liu

In this paper we study stochastic quasi-Newton methods for nonconvex stochastic optimization, where we assume that noisy information about the gradients of the objective function is available via a stochastic first-order oracle (SFO).

General Classification Stochastic Optimization

Local Region Sparse Learning for Image-on-Scalar Regression

no code implementations27 May 2016 Yao Chen, Xiao Wang, Linglong Kong, Hongtu Zhu

Identification of regions of interest (ROI) associated with certain disease has a great impact on public health.

Sparse Learning

Simultaneous Sparse Dictionary Learning and Pruning

no code implementations25 May 2016 Simeng Qu, Xiao Wang

Dictionary learning is a cutting-edge area in imaging processing, that has recently led to state-of-the-art results in many signal processing tasks.

Dictionary Learning Image Denoising

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