Search Results for author: Zheng Zhang

Found 195 papers, 88 papers with code

MovieChats: Chat like Humans in a Closed Domain

no code implementations EMNLP 2020 Hui Su, Xiaoyu Shen, Zhou Xiao, Zheng Zhang, Ernie Chang, Cheng Zhang, Cheng Niu, Jie zhou

In this work, we take a close look at the movie domain and present a large-scale high-quality corpus with fine-grained annotations in hope of pushing the limit of movie-domain chatbots.

Chatbot Retrieval

Region Graph Embedding Network for Zero-Shot Learning

no code implementations ECCV 2020 Guo-Sen Xie, Li Liu, Fan Zhu, Fang Zhao, Zheng Zhang, Yazhou Yao, Jie Qin, Ling Shao

To exploit the progressive interactions among these regions, we represent them as a region graph, on which the parts relation reasoning is performed with graph convolutions, thus leading to our PRR branch.

Graph Embedding Zero-Shot Learning

SSEGCN: Syntactic and Semantic Enhanced Graph Convolutional Network for Aspect-based Sentiment Analysis

1 code implementation NAACL 2022 Zheng Zhang, Zili Zhou, Yanna Wang

Furthermore, to combine syntactic structure and semantic information, we equip the attention score matrices by syntactic mask matrices.

Aspect-Based Sentiment Analysis

ReFresh: Reducing Memory Access from Exploiting Stable Historical Embeddings for Graph Neural Network Training

no code implementations18 Jan 2023 Kezhao Huang, Haitian Jiang, Minjie Wang, Guangxuan Xiao, David Wipf, Xiang Song, Quan Gan, Zengfeng Huang, Jidong Zhai, Zheng Zhang

A key performance bottleneck when training graph neural network (GNN) models on large, real-world graphs is loading node features onto a GPU.

All in Tokens: Unifying Output Space of Visual Tasks via Soft Token

1 code implementation5 Jan 2023 Jia Ning, Chen Li, Zheng Zhang, Zigang Geng, Qi Dai, Kun He, Han Hu

With these new techniques and other designs, we show that the proposed general-purpose task-solver can perform both instance segmentation and depth estimation well.

Instance Segmentation Monocular Depth Estimation +1

TinyMIM: An Empirical Study of Distilling MIM Pre-trained Models

1 code implementation3 Jan 2023 Sucheng Ren, Fangyun Wei, Zheng Zhang, Han Hu

Our TinyMIM model of tiny size achieves 79. 6% top-1 accuracy on ImageNet-1K image classification, which sets a new record for small vision models of the same size and computation budget.

Image Classification Semantic Segmentation

Refined Edge Usage of Graph Neural Networks for Edge Prediction

no code implementations25 Dec 2022 Jiarui Jin, Yangkun Wang, Weinan Zhang, Quan Gan, Xiang Song, Yong Yu, Zheng Zhang, David Wipf

However, existing methods lack elaborate design regarding the distinctions between two tasks that have been frequently overlooked: (i) edges only constitute the topology in the node classification task but can be used as both the topology and the supervisions (i. e., labels) in the edge prediction task; (ii) the node classification makes prediction over each individual node, while the edge prediction is determinated by each pair of nodes.

Link Prediction Node Classification

Policy Transfer via Enhanced Action Space

no code implementations7 Dec 2022 Zheng Zhang, Qingrui Zhang, Bo Zhu, Xiaohan Wang, Tianjiang Hu

Though transfer learning is promising to increase the learning efficiency, the existing methods are still subject to the challenges from long-horizon tasks, especially when expert policies are sub-optimal and partially useful.

Transfer Learning

CBNet: A Plug-and-Play Network for Segmentation-based Scene Text Detection

no code implementations5 Dec 2022 Xi Zhao, Wei Feng, Zheng Zhang, Jingjing Lv, Xin Zhu, Zhangang Lin, Jinghe Hu, Jingping Shao

Recently, segmentation-based methods are quite popular in scene text detection, which mainly contain two steps: text kernel segmentation and expansion.

Scene Text Detection

Exploring Discrete Diffusion Models for Image Captioning

1 code implementation21 Nov 2022 Zixin Zhu, Yixuan Wei, JianFeng Wang, Zhe Gan, Zheng Zhang, Le Wang, Gang Hua, Lijuan Wang, Zicheng Liu, Han Hu

The image captioning task is typically realized by an auto-regressive method that decodes the text tokens one by one.

Image Captioning Image Generation

Could Giant Pretrained Image Models Extract Universal Representations?

no code implementations3 Nov 2022 Yutong Lin, Ze Liu, Zheng Zhang, Han Hu, Nanning Zheng, Stephen Lin, Yue Cao

In this paper, we present a study of frozen pretrained models when applied to diverse and representative computer vision tasks, including object detection, semantic segmentation and video action recognition.

Action Recognition Action Recognition In Videos +5

RLET: A Reinforcement Learning Based Approach for Explainable QA with Entailment Trees

no code implementations31 Oct 2022 Tengxiao Liu, Qipeng Guo, Xiangkun Hu, Yue Zhang, Xipeng Qiu, Zheng Zhang

RLET iteratively performs single step reasoning with sentence selection and deduction generation modules, from which the training signal is accumulated across the tree with elaborately designed aligned reward function that is consistent with the evaluation.

reinforcement-learning reinforcement Learning

DORE: Document Ordered Relation Extraction based on Generative Framework

1 code implementation28 Oct 2022 Qipeng Guo, Yuqing Yang, Hang Yan, Xipeng Qiu, Zheng Zhang

In this paper, we investigate the root cause of the underwhelming performance of the existing generative DocRE models and discover that the culprit is the inadequacy of the training paradigm, instead of the capacities of the models.

Document-level Relation Extraction

Conversation Disentanglement with Bi-Level Contrastive Learning

no code implementations27 Oct 2022 Chengyu Huang, Zheng Zhang, Hao Fei, Lizi Liao

Conversation disentanglement aims to group utterances into detached sessions, which is a fundamental task in processing multi-party conversations.

Contrastive Learning Conversation Disentanglement +1

Self-supervised Amodal Video Object Segmentation

no code implementations23 Oct 2022 Jian Yao, Yuxin Hong, Chiyu Wang, Tianjun Xiao, Tong He, Francesco Locatello, David Wipf, Yanwei Fu, Zheng Zhang

The key intuition is that the occluded part of an object can be explained away if that part is visible in other frames, possibly deformed as long as the deformation can be reasonably learned.

Self-Supervised Learning Semantic Segmentation +3

MR-Based Electrical Property Reconstruction Using Physics-Informed Neural Networks

no code implementations23 Oct 2022 Xinling Yu, José E. C. Serrallés, Ilias I. Giannakopoulos, Ziyue Liu, Luca Daniel, Riccardo Lattanzi, Zheng Zhang

Electrical properties (EP), namely permittivity and electric conductivity, dictate the interactions between electromagnetic waves and biological tissue.

Expediting Large-Scale Vision Transformer for Dense Prediction without Fine-tuning

no code implementations3 Oct 2022 Weicong Liang, Yuhui Yuan, Henghui Ding, Xiao Luo, WeiHong Lin, Ding Jia, Zheng Zhang, Chao Zhang, Han Hu

Vision transformers have recently achieved competitive results across various vision tasks but still suffer from heavy computation costs when processing a large number of tokens.

Depth Estimation Image Classification +4

Whole-Body Lesion Segmentation in 18F-FDG PET/CT

1 code implementation16 Sep 2022 Jia Zhang, Yukun Huang, Zheng Zhang, Yuhang Shi

There has been growing research interest in using deep learning based method to achieve fully automated segmentation of lesion in Positron emission tomography computed tomography(PET CT) scans for the prognosis of various cancers.

Image Segmentation Lesion Segmentation +1

An Empirical Study and Analysis of Learning Generalizable Manipulation Skill in the SAPIEN Simulator

no code implementations31 Aug 2022 Kun Liu, Huiyuan Fu, Zheng Zhang, Huanpu Yin

This paper provides a brief overview of our submission to the no interaction track of SAPIEN ManiSkill Challenge 2021.

A Survey on Incomplete Multi-view Clustering

1 code implementation17 Aug 2022 Jie Wen, Zheng Zhang, Lunke Fei, Bob Zhang, Yong Xu, Zhao Zhang, Jinxing Li

However, in practical applications, such as disease diagnosis, multimedia analysis, and recommendation system, it is common to observe that not all views of samples are available in many cases, which leads to the failure of the conventional multi-view clustering methods.

Incomplete multi-view clustering

Learning Resolution-Adaptive Representations for Cross-Resolution Person Re-Identification

no code implementations9 Jul 2022 Lin Wu, Lingqiao Liu, Yang Wang, Zheng Zhang, Farid Boussaid, Mohammed Bennamoun

It is a challenging and practical problem since the query images often suffer from resolution degradation due to the different capturing conditions from real-world cameras.

Person Re-Identification Super-Resolution

Domain Adaptive Nuclei Instance Segmentation and Classification via Category-aware Feature Alignment and Pseudo-labelling

no code implementations4 Jul 2022 Canran Li, Dongnan Liu, Haoran Li, Zheng Zhang, Guangming Lu, Xiaojun Chang, Weidong Cai

In this work, we propose a novel deep neural network, namely Category-Aware feature alignment and Pseudo-Labelling Network (CAPL-Net) for UDA nuclei instance segmentation and classification.

Classification Instance Segmentation +2

TT-PINN: A Tensor-Compressed Neural PDE Solver for Edge Computing

no code implementations4 Jul 2022 Ziyue Liu, Xinling Yu, Zheng Zhang

Physics-informed neural networks (PINNs) have been increasingly employed due to their capability of modeling complex physics systems.


Self-Healing Robust Neural Networks via Closed-Loop Control

1 code implementation26 Jun 2022 Zhuotong Chen, Qianxiao Li, Zheng Zhang

While numerous attack and defense techniques have been developed, this work investigates the robustness issue from a new angle: can we design a self-healing neural network that can automatically detect and fix the vulnerability issue by itself?

On Data Scaling in Masked Image Modeling

1 code implementation9 Jun 2022 Zhenda Xie, Zheng Zhang, Yue Cao, Yutong Lin, Yixuan Wei, Qi Dai, Han Hu

Our study reveals that: (i) Masked image modeling is also demanding on larger data.

Self-Supervised Learning

Predicting Electricity Infrastructure Induced Wildfire Risk in California

no code implementations6 Jun 2022 Mengqi Yao, Meghana Bharadwaj, Zheng Zhang, Baihong Jin, Duncan S. Callaway

Our data include historical ignition and wire-down points triggered by grid infrastructure collected between 2015 to 2019 in Pacific Gas & Electricity territory along with various weather, vegetation, and very high resolution data on grid infrastructure including location, age, materials.

Weather Forecasting

Contrastive Learning Rivals Masked Image Modeling in Fine-tuning via Feature Distillation

1 code implementation27 May 2022 Yixuan Wei, Han Hu, Zhenda Xie, Zheng Zhang, Yue Cao, Jianmin Bao, Dong Chen, Baining Guo

These properties, which we aggregately refer to as optimization friendliness, are identified and analyzed by a set of attention- and optimization-related diagnosis tools.

Ranked #2 on Instance Segmentation on COCO test-dev (using extra training data)

Contrastive Learning Image Classification +5

Revealing the Dark Secrets of Masked Image Modeling

1 code implementation26 May 2022 Zhenda Xie, Zigang Geng, Jingcheng Hu, Zheng Zhang, Han Hu, Yue Cao

In this paper, we compare MIM with the long-dominant supervised pre-trained models from two perspectives, the visualizations and the experiments, to uncover their key representational differences.

Inductive Bias Monocular Depth Estimation +3

Heterogeneous Information Network based Default Analysis on Banking Micro and Small Enterprise Users

1 code implementation24 Apr 2022 Zheng Zhang, Yingsheng Ji, Jiachen Shen, Xi Zhang, Guangwen Yang

Risk assessment is a substantial problem for financial institutions that has been extensively studied both for its methodological richness and its various practical applications.

Feature Engineering Implicit Relations

Dialogue Meaning Representation for Task-Oriented Dialogue Systems

1 code implementation23 Apr 2022 Xiangkun Hu, Junqi Dai, Hang Yan, Yi Zhang, Qipeng Guo, Xipeng Qiu, Zheng Zhang

We propose Dialogue Meaning Representation (DMR), a pliable and easily extendable representation for task-oriented dialogue.

coreference-resolution Coreference Resolution +1

iCAR: Bridging Image Classification and Image-text Alignment for Visual Recognition

no code implementations22 Apr 2022 Yixuan Wei, Yue Cao, Zheng Zhang, Zhuliang Yao, Zhenda Xie, Han Hu, Baining Guo

Second, we convert the image classification problem from learning parametric category classifier weights to learning a text encoder as a meta network to generate category classifier weights.

Action Recognition Classification +7

BLISS: Robust Sequence-to-Sequence Learning via Self-Supervised Input Representation

no code implementations16 Apr 2022 Zheng Zhang, Liang Ding, Dazhao Cheng, Xuebo Liu, Min Zhang, DaCheng Tao

Data augmentations (DA) are the cores to achieving robust sequence-to-sequence learning on various natural language processing (NLP) tasks.

Grammatical Error Correction Machine Translation +1

Visual Mechanisms Inspired Efficient Transformers for Image and Video Quality Assessment

no code implementations28 Mar 2022 Junyong You, Zheng Zhang

Meanwhile, representative features for image quality perception in the spatial and frequency domains can also be derived from the IQA model, which are then fed into another windowed transformer architecture for video quality assessment (VQA).

Image Quality Assessment Video Quality Assessment +1

Multi-robot Cooperative Pursuit via Potential Field-Enhanced Reinforcement Learning

no code implementations9 Mar 2022 Zheng Zhang, Xiaohan Wang, Qingrui Zhang, Tianjiang Hu

It is shown by numerical simulations that the proposed hybrid design outperforms the pursuit policies either learned from vanilla reinforcement learning or designed by the potential field method.

reinforcement-learning reinforcement Learning

StoryBuddy: A Human-AI Collaborative Chatbot for Parent-Child Interactive Storytelling with Flexible Parental Involvement

no code implementations13 Feb 2022 Zheng Zhang, Ying Xu, Yanhao Wang, Bingsheng Yao, Daniel Ritchie, Tongshuang Wu, Mo Yu, Dakuo Wang, Toby Jia-Jun Li

Despite its benefits for children's skill development and parent-child bonding, many parents do not often engage in interactive storytelling by having story-related dialogues with their child due to limited availability or challenges in coming up with appropriate questions.


Online, Informative MCMC Thinning with Kernelized Stein Discrepancy

1 code implementation18 Jan 2022 Cole Hawkins, Alec Koppel, Zheng Zhang

A fundamental challenge in Bayesian inference is efficient representation of a target distribution.

Bayesian Inference

A Critical Review of Inductive Logic Programming Techniques for Explainable AI

no code implementations31 Dec 2021 Zheng Zhang, Levent Yilmaz, Bo Liu

Despite recent advances in modern machine learning algorithms, the opaqueness of their underlying mechanisms continues to be an obstacle in adoption.

BIG-bench Machine Learning Explainable artificial intelligence +2

A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-language Model

1 code implementation29 Dec 2021 Mengde Xu, Zheng Zhang, Fangyun Wei, Yutong Lin, Yue Cao, Han Hu, Xiang Bai

However, semantic segmentation and the CLIP model perform on different visual granularity, that semantic segmentation processes on pixels while CLIP performs on images.

Image Classification Language Modelling +5

Representation Learning on Spatial Networks

1 code implementation NeurIPS 2021 Zheng Zhang, Liang Zhao

Specifically, a provably information-lossless and roto-translation invariant representation of spatial information on networks is presented.

Representation Learning Translation

SimMIM: A Simple Framework for Masked Image Modeling

2 code implementations CVPR 2022 Zhenda Xie, Zheng Zhang, Yue Cao, Yutong Lin, Jianmin Bao, Zhuliang Yao, Qi Dai, Han Hu

We also leverage this approach to facilitate the training of a 3B model (SwinV2-G), that by $40\times$ less data than that in previous practice, we achieve the state-of-the-art on four representative vision benchmarks.

Representation Learning Self-Supervised Image Classification

Swin Transformer V2: Scaling Up Capacity and Resolution

14 code implementations CVPR 2022 Ze Liu, Han Hu, Yutong Lin, Zhuliang Yao, Zhenda Xie, Yixuan Wei, Jia Ning, Yue Cao, Zheng Zhang, Li Dong, Furu Wei, Baining Guo

Three main techniques are proposed: 1) a residual-post-norm method combined with cosine attention to improve training stability; 2) A log-spaced continuous position bias method to effectively transfer models pre-trained using low-resolution images to downstream tasks with high-resolution inputs; 3) A self-supervised pre-training method, SimMIM, to reduce the needs of vast labeled images.

Ranked #3 on Instance Segmentation on COCO minival (using extra training data)

Action Classification Image Classification +3

Bootstrap Your Object Detector via Mixed Training

1 code implementation NeurIPS 2021 Mengde Xu, Zheng Zhang, Fangyun Wei, Yutong Lin, Yue Cao, Stephen Lin, Han Hu, Xiang Bai

We introduce MixTraining, a new training paradigm for object detection that can improve the performance of existing detectors for free.

Data Augmentation object-detection +1

Why Propagate Alone? Parallel Use of Labels and Features on Graphs

no code implementations ICLR 2022 Yangkun Wang, Jiarui Jin, Weinan Zhang, Yongyi Yang, Jiuhai Chen, Quan Gan, Yong Yu, Zheng Zhang, Zengfeng Huang, David Wipf

In this regard, it has recently been proposed to use a randomly-selected portion of the training labels as GNN inputs, concatenated with the original node features for making predictions on the remaining labels.

Node Property Prediction

Inductive Relation Prediction Using Analogy Subgraph Embeddings

no code implementations ICLR 2022 Jiarui Jin, Yangkun Wang, Kounianhua Du, Weinan Zhang, Zheng Zhang, David Wipf, Yong Yu, Quan Gan

Prevailing methods for relation prediction in heterogeneous graphs aim at learning latent representations (i. e., embeddings) of observed nodes and relations, and thus are limited to the transductive setting where the relation types must be known during training.

Inductive Bias Inductive Relation Prediction

Kokoyi: Executable LaTeX for End-to-end Deep Learning

no code implementations29 Sep 2021 Minjie Wang, Haoming Lu, Yu Gai, Lesheng Jin, Zihao Ye, Zheng Zhang

Despite substantial efforts from the deep learning system community to relieve researchers and practitioners from the burden of implementing models with ever-growing complexity, a considerable lingual gap remains between developing models in the language of mathematics and implementing them in the languages of computer.


Deep Collaborative Multi-Modal Learning for Unsupervised Kinship Estimation

no code implementations7 Sep 2021 Guan-Nan Dong, Chi-Man Pun, Zheng Zhang

To this end, we propose a novel deep collaborative multi-modal learning (DCML) to integrate the underlying information presented in facial properties in an adaptive manner to strengthen the facial details for effective unsupervised kinship verification.

Face Recognition

Kinship Verification Based on Cross-Generation Feature Interaction Learning

no code implementations7 Sep 2021 Guan-Nan Dong, Chi-Man Pun, Zheng Zhang

Specifically, we take parents and children as a whole to extract the expressive local and non-local features.

EVA: An Open-Domain Chinese Dialogue System with Large-Scale Generative Pre-Training

2 code implementations3 Aug 2021 Hao Zhou, Pei Ke, Zheng Zhang, Yuxian Gu, Yinhe Zheng, Chujie Zheng, Yida Wang, Chen Henry Wu, Hao Sun, Xiaocong Yang, Bosi Wen, Xiaoyan Zhu, Minlie Huang, Jie Tang

Although pre-trained language models have remarkably enhanced the generation ability of dialogue systems, open-domain Chinese dialogue systems are still limited by the dialogue data and the model size compared with English ones.

Learning Hierarchical Graph Neural Networks for Image Clustering

2 code implementations ICCV 2021 Yifan Xing, Tong He, Tianjun Xiao, Yongxin Wang, Yuanjun Xiong, Wei Xia, David Wipf, Zheng Zhang, Stefano Soatto

Our hierarchical GNN uses a novel approach to merge connected components predicted at each level of the hierarchy to form a new graph at the next level.

Face Clustering

Context-Aware Attention-Based Data Augmentation for POI Recommendation

no code implementations30 Jun 2021 Yang Li, Yadan Luo, Zheng Zhang, Shazia W. Sadiq, Peng Cui

It aims at suggesting the next POI to a user in spatial and temporal context, which is a practical yet challenging task in various applications.

Data Augmentation

Video Swin Transformer

12 code implementations CVPR 2022 Ze Liu, Jia Ning, Yue Cao, Yixuan Wei, Zheng Zhang, Stephen Lin, Han Hu

The vision community is witnessing a modeling shift from CNNs to Transformers, where pure Transformer architectures have attained top accuracy on the major video recognition benchmarks.

Ranked #20 on Action Classification on Kinetics-600 (using extra training data)

Action Classification Action Recognition +4

End-to-End Semi-Supervised Object Detection with Soft Teacher

5 code implementations ICCV 2021 Mengde Xu, Zheng Zhang, Han Hu, JianFeng Wang, Lijuan Wang, Fangyun Wei, Xiang Bai, Zicheng Liu

This paper presents an end-to-end semi-supervised object detection approach, in contrast to previous more complex multi-stage methods.

Instance Segmentation object-detection +4

DS-TransUNet:Dual Swin Transformer U-Net for Medical Image Segmentation

1 code implementation12 Jun 2021 Ailiang Lin, Bingzhi Chen, Jiayu Xu, Zheng Zhang, Guangming Lu

To alleviate these problems, we propose a novel deep medical image segmentation framework called Dual Swin Transformer U-Net (DS-TransUNet), which might be the first attempt to concurrently incorporate the advantages of hierarchical Swin Transformer into both encoder and decoder of the standard U-shaped architecture to enhance the semantic segmentation quality of varying medical images.

Image Segmentation Medical Image Segmentation +1

A Unified Generative Framework for Various NER Subtasks

1 code implementation ACL 2021 Hang Yan, Tao Gui, Junqi Dai, Qipeng Guo, Zheng Zhang, Xipeng Qiu

To that end, we propose to formulate the NER subtasks as an entity span sequence generation task, which can be solved by a unified sequence-to-sequence (Seq2Seq) framework.

named-entity-recognition NER +1

Prototype-supervised Adversarial Network for Targeted Attack of Deep Hashing

1 code implementation CVPR 2021 Xunguang Wang, Zheng Zhang, Baoyuan Wu, Fumin Shen, Guangming Lu

However, deep hashing networks are vulnerable to adversarial examples, which is a practical secure problem but seldom studied in hashing-based retrieval field.

Image Retrieval Representation Learning +1

3U-EdgeAI: Ultra-Low Memory Training, Ultra-Low BitwidthQuantization, and Ultra-Low Latency Acceleration

no code implementations11 May 2021 Yao Chen, Cole Hawkins, Kaiqi Zhang, Zheng Zhang, Cong Hao

This paper emphasizes the importance and efficacy of training, quantization and accelerator design, and calls for more research breakthroughs in the area for AI on the edge.

Model Compression Quantization

Group-Free 3D Object Detection via Transformers

3 code implementations ICCV 2021 Ze Liu, Zheng Zhang, Yue Cao, Han Hu, Xin Tong

Instead of grouping local points to each object candidate, our method computes the feature of an object from all the points in the point cloud with the help of an attention mechanism in the Transformers \cite{vaswani2017attention}, where the contribution of each point is automatically learned in the network training.

3D Object Detection object-detection

High-Dimensional Uncertainty Quantification via Tensor Regression with Rank Determination and Adaptive Sampling

no code implementations31 Mar 2021 Zichang He, Zheng Zhang

Recently, low-rank tensor methods have been developed to mitigate this issue, but two fundamental challenges remain open: how to automatically determine the tensor rank and how to adaptively pick the informative simulation samples.


Bag of Tricks for Node Classification with Graph Neural Networks

1 code implementation24 Mar 2021 Yangkun Wang, Jiarui Jin, Weinan Zhang, Yong Yu, Zheng Zhang, David Wipf

Over the past few years, graph neural networks (GNN) and label propagation-based methods have made significant progress in addressing node classification tasks on graphs.

Classification General Classification +2

Graph Neural Networks Inspired by Classical Iterative Algorithms

1 code implementation10 Mar 2021 Yongyi Yang, Tang Liu, Yangkun Wang, Jinjing Zhou, Quan Gan, Zhewei Wei, Zheng Zhang, Zengfeng Huang, David Wipf

Despite the recent success of graph neural networks (GNN), common architectures often exhibit significant limitations, including sensitivity to oversmoothing, long-range dependencies, and spurious edges, e. g., as can occur as a result of graph heterophily or adversarial attacks.

Node Classification

A Unified Framework for Specification Tests of Continuous Treatment Effect Models

no code implementations16 Feb 2021 Wei Huang, Oliver Linton, Zheng Zhang

We propose a general framework for the specification testing of continuous treatment effect models.

Bayesian Inference with Certifiable Adversarial Robustness

1 code implementation10 Feb 2021 Matthew Wicker, Luca Laurenti, Andrea Patane, Zhoutong Chen, Zheng Zhang, Marta Kwiatkowska

We consider adversarial training of deep neural networks through the lens of Bayesian learning, and present a principled framework for adversarial training of Bayesian Neural Networks (BNNs) with certifiable guarantees.

Adversarial Robustness Bayesian Inference

Towards Robust Neural Networks via Close-loop Control

1 code implementation ICLR 2021 Zhuotong Chen, Qianxiao Li, Zheng Zhang

We connect the robustness of neural networks with optimal control using the geometrical information of underlying data to design the control objective.

Semantics Disentangling for Generalized Zero-Shot Learning

1 code implementation ICCV 2021 Zhi Chen, Yadan Luo, Ruihong Qiu, Sen Wang, Zi Huang, Jingjing Li, Zheng Zhang

Generalized zero-shot learning (GZSL) aims to classify samples under the assumption that some classes are not observable during training.

Generalized Zero-Shot Learning

Entropy-Based Uncertainty Calibration for Generalized Zero-Shot Learning

no code implementations9 Jan 2021 Zhi Chen, Zi Huang, Jingjing Li, Zheng Zhang

To address these issues, in this paper, we propose a novel framework that leverages dual variational autoencoders with a triplet loss to learn discriminative latent features and applies the entropy-based calibration to minimize the uncertainty in the overlapped area between the seen and unseen classes.

Generalized Zero-Shot Learning

Composite Adversarial Training for Multiple Adversarial Perturbations and Beyond

no code implementations1 Jan 2021 Xinyang Zhang, Zheng Zhang, Ting Wang

One intriguing property of deep neural networks (DNNs) is their vulnerability to adversarial perturbations.

Explore with Dynamic Map: Graph Structured Reinforcement Learning

no code implementations1 Jan 2021 Jiarui Jin, Sijin Zhou, Weinan Zhang, Rasool Fakoor, David Wipf, Tong He, Yong Yu, Zheng Zhang, Alex Smola

In reinforcement learning, a map with states and transitions built based on historical trajectories is often helpful in exploration and exploitation.

reinforcement-learning reinforcement Learning

Active Sampling for Accelerated MRI with Low-Rank Tensors

no code implementations23 Dec 2020 Zichang He, Bo Zhao, Zheng Zhang

In this paper, we introduce an active low-rank tensor model for fast MR imaging.

TrojanZoo: Towards Unified, Holistic, and Practical Evaluation of Neural Backdoors

1 code implementation16 Dec 2020 Ren Pang, Zheng Zhang, Xiangshan Gao, Zhaohan Xi, Shouling Ji, Peng Cheng, Xiapu Luo, Ting Wang

To bridge this gap, we design and implement TROJANZOO, the first open-source platform for evaluating neural backdoor attacks/defenses in a unified, holistic, and practical manner.

Fork or Fail: Cycle-Consistent Training with Many-to-One Mappings

1 code implementation14 Dec 2020 Qipeng Guo, Zhijing Jin, Ziyu Wang, Xipeng Qiu, Weinan Zhang, Jun Zhu, Zheng Zhang, David Wipf

Cycle-consistent training is widely used for jointly learning a forward and inverse mapping between two domains of interest without the cumbersome requirement of collecting matched pairs within each domain.

Knowledge Graphs Text Generation

Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learning

7 code implementations CVPR 2021 Zhenda Xie, Yutong Lin, Zheng Zhang, Yue Cao, Stephen Lin, Han Hu

We argue that the power of contrastive learning has yet to be fully unleashed, as current methods are trained only on instance-level pretext tasks, leading to representations that may be sub-optimal for downstream tasks requiring dense pixel predictions.

Contrastive Learning object-detection +3

DistDGL: Distributed Graph Neural Network Training for Billion-Scale Graphs

1 code implementation11 Oct 2020 Da Zheng, Chao Ma, Minjie Wang, Jinjing Zhou, Qidong Su, Xiang Song, Quan Gan, Zheng Zhang, George Karypis

To minimize the overheads associated with distributed computations, DistDGL uses a high-quality and light-weight min-cut graph partitioning algorithm along with multiple balancing constraints.

Fraud Detection graph partitioning

CoLAKE: Contextualized Language and Knowledge Embedding

1 code implementation COLING 2020 Tianxiang Sun, Yunfan Shao, Xipeng Qiu, Qipeng Guo, Yaru Hu, Xuanjing Huang, Zheng Zhang

With the emerging branch of incorporating factual knowledge into pre-trained language models such as BERT, most existing models consider shallow, static, and separately pre-trained entity embeddings, which limits the performance gains of these models.

Entity Embeddings Knowledge Graph Completion +1

Casual inference of General Treatment Effects using Neural Networks with A Diverging Number of Confounders

no code implementations15 Sep 2020 Xiaohong Chen, Ying Liu, Shujie Ma, Zheng Zhang

The estimation of causal effects is a primary goal of behavioral, social, economic and biomedical sciences.

Dual-constrained Deep Semi-Supervised Coupled Factorization Network with Enriched Prior

no code implementations8 Sep 2020 Yan Zhang, Zhao Zhang, Yang Wang, Zheng Zhang, Li Zhang, Shuicheng Yan, Meng Wang

Nonnegative matrix factorization is usually powerful for learning the "shallow" parts-based representation, but it clearly fails to discover deep hierarchical information within both the basis and representation spaces.

Graph Learning Representation Learning

FeatGraph: A Flexible and Efficient Backend for Graph Neural Network Systems

no code implementations26 Aug 2020 Yuwei Hu, Zihao Ye, Minjie Wang, Jiali Yu, Da Zheng, Mu Li, Zheng Zhang, Zhiru Zhang, Yida Wang

FeatGraph provides a flexible programming interface to express diverse GNN models by composing coarse-grained sparse templates with fine-grained user-defined functions (UDFs) on each vertex/edge.

Trojaning Language Models for Fun and Profit

1 code implementation1 Aug 2020 Xinyang Zhang, Zheng Zhang, Shouling Ji, Ting Wang

Recent years have witnessed the emergence of a new paradigm of building natural language processing (NLP) systems: general-purpose, pre-trained language models (LMs) are composed with simple downstream models and fine-tuned for a variety of NLP tasks.

Question Answering Specificity +1

Adversarial Bipartite Graph Learning for Video Domain Adaptation

1 code implementation31 Jul 2020 Yadan Luo, Zi Huang, Zijian Wang, Zheng Zhang, Mahsa Baktashmotlagh

To further enhance the model capacity and testify the robustness of the proposed architecture on difficult transfer tasks, we extend our model to work in a semi-supervised setting using an additional video-level bipartite graph.

Domain Adaptation Graph Learning +1

RepPoints V2: Verification Meets Regression for Object Detection

1 code implementation NeurIPS 2020 Yihong Chen, Zheng Zhang, Yue Cao, Li-Wei Wang, Stephen Lin, Han Hu

Though RepPoints provides high performance, we find that its heavy reliance on regression for object localization leaves room for improvement.

Instance Segmentation object-detection +5

A Closer Look at Local Aggregation Operators in Point Cloud Analysis

1 code implementation ECCV 2020 Ze Liu, Han Hu, Yue Cao, Zheng Zhang, Xin Tong

Our investigation reveals that despite the different designs of these operators, all of these operators make surprisingly similar contributions to the network performance under the same network input and feature numbers and result in the state-of-the-art accuracy on standard benchmarks.

3D Semantic Segmentation

An Efficient Neighborhood-based Interaction Model for Recommendation on Heterogeneous Graph

1 code implementation1 Jul 2020 Jiarui Jin, Jiarui Qin, Yuchen Fang, Kounianhua Du, Wei-Nan Zhang, Yong Yu, Zheng Zhang, Alexander J. Smola

To the best of our knowledge, this is the first work providing an efficient neighborhood-based interaction model in the HIN-based recommendations.

Recommendation Systems

Disentangled Non-Local Neural Networks

4 code implementations ECCV 2020 Minghao Yin, Zhuliang Yao, Yue Cao, Xiu Li, Zheng Zhang, Stephen Lin, Han Hu

This paper first studies the non-local block in depth, where we find that its attention computation can be split into two terms, a whitened pairwise term accounting for the relationship between two pixels and a unary term representing the saliency of every pixel.

Action Recognition object-detection +2

Dual-level Semantic Transfer Deep Hashing for Efficient Social Image Retrieval

1 code implementation10 Jun 2020 Lei Zhu, Hui Cui, Zhiyong Cheng, Jingjing Li, Zheng Zhang

Specifically, we design a complementary dual-level semantic transfer mechanism to efficiently discover the potential semantics of tags and seamlessly transfer them into binary hash codes.

Image Retrieval Representation Learning +1

CycleGT: Unsupervised Graph-to-Text and Text-to-Graph Generation via Cycle Training

2 code implementations ACL (WebNLG, INLG) 2020 Qipeng Guo, Zhijing Jin, Xipeng Qiu, Wei-Nan Zhang, David Wipf, Zheng Zhang

Due to the difficulty and high cost of data collection, the supervised data available in the two fields are usually on the magnitude of tens of thousands, for example, 18K in the WebNLG~2017 dataset after preprocessing, which is far fewer than the millions of data for other tasks such as machine translation.

Graph Generation Knowledge Graphs +2

Repurpose Open Data to Discover Therapeutics for COVID-19 using Deep Learning

no code implementations21 May 2020 Xiangxiang Zeng, Xiang Song, Tengfei Ma, Xiaoqin Pan, Yadi Zhou, Yuan Hou, Zheng Zhang, George Karypis, Feixiong Cheng

While this study, by no means recommends specific drugs, it demonstrates a powerful deep learning methodology to prioritize existing drugs for further investigation, which holds the potential of accelerating therapeutic development for COVID-19.


Learning Goal-oriented Dialogue Policy with Opposite Agent Awareness

no code implementations Asian Chapter of the Association for Computational Linguistics 2020 Zheng Zhang, Lizi Liao, Xiaoyan Zhu, Tat-Seng Chua, Zitao Liu, Yan Huang, Minlie Huang

Most existing approaches for goal-oriented dialogue policy learning used reinforcement learning, which focuses on the target agent policy and simply treat the opposite agent policy as part of the environment.

Decision Making

DGL-KE: Training Knowledge Graph Embeddings at Scale

1 code implementation18 Apr 2020 Da Zheng, Xiang Song, Chao Ma, Zeyuan Tan, Zihao Ye, Jin Dong, Hao Xiong, Zheng Zhang, George Karypis

Experiments on knowledge graphs consisting of over 86M nodes and 338M edges show that DGL-KE can compute embeddings in 100 minutes on an EC2 instance with 8 GPUs and 30 minutes on an EC2 cluster with 4 machines with 48 cores/machine.

Distributed, Parallel, and Cluster Computing

Task-adaptive Asymmetric Deep Cross-modal Hashing

no code implementations1 Apr 2020 Fengling Li, Tong Wang, Lei Zhu, Zheng Zhang, Xinhua Wang

Unlike previous cross-modal hashing approaches, our learning framework jointly optimizes semantic preserving that transforms deep features of multimedia data into binary hash codes, and the semantic regression which directly regresses query modality representation to explicit label.

Cross-Modal Retrieval Retrieval

Spatially Adaptive Inference with Stochastic Feature Sampling and Interpolation

1 code implementation ECCV 2020 Zhenda Xie, Zheng Zhang, Xizhou Zhu, Gao Huang, Stephen Lin

In the feature maps of CNNs, there commonly exists considerable spatial redundancy that leads to much repetitive processing.

Recent Advances and Challenges in Task-oriented Dialog System

no code implementations17 Mar 2020 Zheng Zhang, Ryuichi Takanobu, Qi Zhu, Minlie Huang, Xiaoyan Zhu

Due to the significance and value in human-computer interaction and natural language processing, task-oriented dialog systems are attracting more and more attention in both academic and industrial communities.

CrossWOZ: A Large-Scale Chinese Cross-Domain Task-Oriented Dialogue Dataset

2 code implementations TACL 2020 Qi Zhu, Kaili Huang, Zheng Zhang, Xiaoyan Zhu, Minlie Huang

To advance multi-domain (cross-domain) dialogue modeling as well as alleviate the shortage of Chinese task-oriented datasets, we propose CrossWOZ, the first large-scale Chinese Cross-Domain Wizard-of-Oz task-oriented dataset.

Dialogue State Tracking Task-Oriented Dialogue Systems

Transformer on a Diet

1 code implementation14 Feb 2020 Chenguang Wang, Zihao Ye, Aston Zhang, Zheng Zhang, Alexander J. Smola

Transformer has been widely used thanks to its ability to capture sequence information in an efficient way.

Language Modelling

ConvLab-2: An Open-Source Toolkit for Building, Evaluating, and Diagnosing Dialogue Systems

1 code implementation ACL 2020 Qi Zhu, Zheng Zhang, Yan Fang, Xiang Li, Ryuichi Takanobu, Jinchao Li, Baolin Peng, Jianfeng Gao, Xiaoyan Zhu, Minlie Huang

We present ConvLab-2, an open-source toolkit that enables researchers to build task-oriented dialogue systems with state-of-the-art models, perform an end-to-end evaluation, and diagnose the weakness of systems.

Task-Oriented Dialogue Systems

Dense Residual Network: Enhancing Global Dense Feature Flow for Character Recognition

no code implementations23 Jan 2020 Zhao Zhang, Zemin Tang, Yang Wang, Zheng Zhang, Choujun Zhan, ZhengJun Zha, Meng Wang

To construct FDRN, we propose a new fast residual dense block (f-RDB) to retain the ability of local feature fusion and local residual learning of original RDB, which can reduce the computing efforts at the same time.

Dense RepPoints: Representing Visual Objects with Dense Point Sets

2 code implementations ECCV 2020 Ze Yang, Yinghao Xu, Han Xue, Zheng Zhang, Raquel Urtasun, Li-Wei Wang, Stephen Lin, Han Hu

We present a new object representation, called Dense RepPoints, that utilizes a large set of points to describe an object at multiple levels, including both box level and pixel level.

Object Detection

Fully-Convolutional Intensive Feature Flow Neural Network for Text Recognition

no code implementations13 Dec 2019 Zhao Zhang, Zemin Tang, Zheng Zhang, Yang Wang, Jie Qin, Meng Wang

But existing CNNs based frameworks still have several drawbacks: 1) the traditaional pooling operation may lose important feature information and is unlearnable; 2) the tradi-tional convolution operation optimizes slowly and the hierar-chical features from different layers are not fully utilized.

Deep Self-representative Concept Factorization Network for Representation Learning

no code implementations13 Dec 2019 Yan Zhang, Zhao Zhang, Zheng Zhang, Mingbo Zhao, Li Zhang, Zheng-Jun Zha, Meng Wang

In this paper, we investigate the unsupervised deep representation learning issue and technically propose a novel framework called Deep Self-representative Concept Factorization Network (DSCF-Net), for clustering deep features.

Representation Learning

Quantum-Inspired Hamiltonian Monte Carlo for Bayesian Sampling

1 code implementation4 Dec 2019 Ziming Liu, Zheng Zhang

Hamiltonian Monte Carlo (HMC) is an efficient Bayesian sampling method that can make distant proposals in the parameter space by simulating a Hamiltonian dynamical system.

BIG-bench Machine Learning Image Denoising +1

Multi-Scale Self-Attention for Text Classification

no code implementations2 Dec 2019 Qipeng Guo, Xipeng Qiu, PengFei Liu, xiangyang xue, Zheng Zhang

In this paper, we introduce the prior knowledge, multi-scale structure, into self-attention modules.

Classification General Classification +2

Discriminative Local Sparse Representation by Robust Adaptive Dictionary Pair Learning

no code implementations20 Nov 2019 Yulin Sun, Zhao Zhang, Weiming Jiang, Zheng Zhang, Li Zhang, Shuicheng Yan, Meng Wang

In this paper, we propose a structured Robust Adaptive Dic-tionary Pair Learning (RA-DPL) framework for the discrim-inative sparse representation learning.

Representation Learning

Transductive Zero-Shot Hashing for Multilabel Image Retrieval

1 code implementation17 Nov 2019 Qin Zou, Zheng Zhang, Ling Cao, Long Chen, Song Wang

Given semantic annotations such as class labels and pairwise similarities of the training data, hashing methods can learn and generate effective and compact binary codes.

Multi-Label Image Retrieval Quantization +1

Learning from the Past: Continual Meta-Learning via Bayesian Graph Modeling

no code implementations12 Nov 2019 Yadan Luo, Zi Huang, Zheng Zhang, Ziwei Wang, Mahsa Baktashmotlagh, Yang Yang

Meta-learning for few-shot learning allows a machine to leverage previously acquired knowledge as a prior, thus improving the performance on novel tasks with only small amounts of data.

Continual Learning Few-Shot Learning

Deep Collaborative Discrete Hashing with Semantic-Invariant Structure

no code implementations5 Nov 2019 Zijian Wang, Zheng Zhang, Yadan Luo, Zi Huang

Existing deep hashing approaches fail to fully explore semantic correlations and neglect the effect of linguistic context on visual attention learning, leading to inferior performance.

Active Subspace of Neural Networks: Structural Analysis and Universal Attacks

1 code implementation29 Oct 2019 Chunfeng Cui, Kaiqi Zhang, Talgat Daulbaev, Julia Gusak, Ivan Oseledets, Zheng Zhang

Secondly, we propose analyzing the vulnerability of a neural network using active subspace and finding an additive universal adversarial attack vector that can misclassify a dataset with a high probability.

Adversarial Attack

Adaptive Structure-constrained Robust Latent Low-Rank Coding for Image Recovery

no code implementations21 Aug 2019 Zhao Zhang, Lei Wang, Sheng Li, Yang Wang, Zheng Zhang, Zheng-Jun Zha, Meng Wang

Specifically, AS-LRC performs the latent decomposition of given data into a low-rank reconstruction by a block-diagonal codes matrix, a group sparse locality-adaptive salient feature part and a sparse error part.

Representation Learning

Learning Structured Twin-Incoherent Twin-Projective Latent Dictionary Pairs for Classification

no code implementations21 Aug 2019 Zhao Zhang, Yulin Sun, Zheng Zhang, Yang Wang, Guangcan Liu, Meng Wang

In this setting, our TP-DPL integrates the twin-incoherence based latent flexible DPL and the joint embedding of codes as well as salient features by twin-projection into a unified model in an adaptive neighborhood-preserving manner.

General Classification

Curiosity-driven Reinforcement Learning for Diverse Visual Paragraph Generation

no code implementations1 Aug 2019 Yadan Luo, Zi Huang, Zheng Zhang, Ziwei Wang, Jingjing Li, Yang Yang

Visual paragraph generation aims to automatically describe a given image from different perspectives and organize sentences in a coherent way.

Imitation Learning reinforcement-learning +1

Tucker Tensor Decomposition on FPGA

no code implementations28 Jun 2019 Kaiqi Zhang, Xiyuan Zhang, Zheng Zhang

This paper presents an hardware accelerator for a classical tensor computation framework, Tucker decomposition.

Signal Processing Hardware Architecture

Joint Subspace Recovery and Enhanced Locality Driven Robust Flexible Discriminative Dictionary Learning

no code implementations11 Jun 2019 Zhao Zhang, Jiahuan Ren, Weiming Jiang, Zheng Zhang, Richang Hong, Shuicheng Yan, Meng Wang

We propose a joint subspace recovery and enhanced locality based robust flexible label consistent dictionary learning method called Robust Flexible Discriminative Dictionary Learning (RFDDL).

Dictionary Learning

Scalable Block-Diagonal Locality-Constrained Projective Dictionary Learning

no code implementations25 May 2019 Zhao Zhang, Weiming Jiang, Zheng Zhang, Sheng Li, Guangcan Liu, Jie Qin

More importantly, LC-PDL avoids using the complementary data matrix to learn the sub-dictionary over each class.

Dictionary Learning

Bayesian Tensorized Neural Networks with Automatic Rank Selection

1 code implementation24 May 2019 Cole Hawkins, Zheng Zhang

Tensor decomposition is an effective approach to compress over-parameterized neural networks and to enable their deployment on resource-constrained hardware platforms.

Model Compression Tensor Decomposition

Gradient-based learning for F-measure and other performance metrics

no code implementations ICLR 2019 Yu Gai, Zheng Zhang, Kyunghyun Cho

Many important classification performance metrics, e. g. $F$-measure, are non-differentiable and non-decomposable, and are thus unfriendly to gradient descent algorithm.

General Classification

Spatial-Temporal Relation Networks for Multi-Object Tracking

no code implementations ICCV 2019 Jiarui Xu, Yue Cao, Zheng Zhang, Han Hu

Recent progress in multiple object tracking (MOT) has shown that a robust similarity score is key to the success of trackers.

Multi-Object Tracking Multiple Object Tracking

ConvLab: Multi-Domain End-to-End Dialog System Platform

2 code implementations ACL 2019 Sungjin Lee, Qi Zhu, Ryuichi Takanobu, Xiang Li, Yaoqin Zhang, Zheng Zhang, Jinchao Li, Baolin Peng, Xiujun Li, Minlie Huang, Jianfeng Gao

We present ConvLab, an open-source multi-domain end-to-end dialog system platform, that enables researchers to quickly set up experiments with reusable components and compare a large set of different approaches, ranging from conventional pipeline systems to end-to-end neural models, in common environments.

An Empirical Study of Spatial Attention Mechanisms in Deep Networks

1 code implementation ICCV 2019 Xizhou Zhu, Dazhi Cheng, Zheng Zhang, Stephen Lin, Jifeng Dai

Attention mechanisms have become a popular component in deep neural networks, yet there has been little examination of how different influencing factors and methods for computing attention from these factors affect performance.