Search Results for author: Jian Tang

Found 131 papers, 55 papers with code

Few-shot Relation Extraction via Bayesian Meta-learning on Task Graphs

no code implementations ICML 2020 Meng Qu, Tianyu Gao, Louis-Pascal Xhonneux, Jian Tang

This paper studies few-shot relation extraction, which aims at predicting the relation for a pair of entities in a sentence by training with a few labeled examples in each relation.

Meta-Learning Relation Extraction

Learning to Navigate in Synthetically Accessible Chemical Space Using Reinforcement Learning

1 code implementation ICML 2020 Sai Krishna Gottipati, Boris Sattarov, Sufeng. Niu, Hao-Ran Wei, Yashaswi Pathak, Shengchao Liu, Simon Blackburn, Karam Thomas, Connor Coley, Jian Tang, Sarath Chandar, Yoshua Bengio

In this work, we propose a novel reinforcement learning (RL) setup for drug discovery that addresses this challenge by embedding the concept of synthetic accessibility directly into the de novo compound design system.

Drug Discovery reinforcement-learning

Neural Structured Prediction for Inductive Node Classification

1 code implementation ICLR 2022 Meng Qu, Huiyu Cai, Jian Tang

This problem has been extensively studied with graph neural networks (GNNs) by learning effective node representations, as well as traditional structured prediction methods for modeling the structured output of node labels, e. g., conditional random fields (CRFs).

Classification Node Classification +1

Weakly-supervised Temporal Path Representation Learning with Contrastive Curriculum Learning -- Extended Version

1 code implementation30 Mar 2022 Sean Bin Yang, Chenjuan Guo, Jilin Hu, Bin Yang, Jian Tang, Christian S. Jensen

In this setting, it is essential to learn generic temporal path representations(TPRs) that consider spatial and temporal correlations simultaneously and that can be used in different applications, i. e., downstream tasks.

Contrastive Learning Representation Learning

RGB-Depth Fusion GAN for Indoor Depth Completion

no code implementations21 Mar 2022 Haowen Wang, Mingyuan Wang, Zhengping Che, Zhiyuan Xu, XIUQUAN QIAO, Mengshi Qi, Feifei Feng, Jian Tang

In this paper, we design a novel two-branch end-to-end fusion network, which takes a pair of RGB and incomplete depth images as input to predict a dense and completed depth map.

Depth Completion Transparent objects

Protein Representation Learning by Geometric Structure Pretraining

no code implementations11 Mar 2022 Zuobai Zhang, Minghao Xu, Arian Jamasb, Vijil Chenthamarakshan, Aurelie Lozano, Payel Das, Jian Tang

Learning effective protein representations is critical in a variety of tasks in biology such as predicting protein function or structure.

Contrastive Learning Representation Learning

GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generation

1 code implementation ICLR 2022 Minkai Xu, Lantao Yu, Yang song, Chence Shi, Stefano Ermon, Jian Tang

GeoDiff treats each atom as a particle and learns to directly reverse the diffusion process (i. e., transforming from a noise distribution to stable conformations) as a Markov chain.

Drug Discovery

Structured Multi-task Learning for Molecular Property Prediction

1 code implementation22 Feb 2022 Shengchao Liu, Meng Qu, Zuobai Zhang, Huiyu Cai, Jian Tang

However, in contrast to other domains, the performance of multi-task learning in drug discovery is still not satisfying as the number of labeled data for each task is too limited, which calls for additional data to complement the data scarcity.

Drug Discovery Molecular Property Prediction +2

CADRE: A Cascade Deep Reinforcement Learning Framework for Vision-based Autonomous Urban Driving

no code implementations17 Feb 2022 Yinuo Zhao, Kun Wu, Zhiyuan Xu, Zhengping Che, Qi Lu, Jian Tang, Chi Harold Liu

Vision-based autonomous urban driving in dense traffic is quite challenging due to the complicated urban environment and the dynamics of the driving behaviors.

reinforcement-learning

TorchDrug: A Powerful and Flexible Machine Learning Platform for Drug Discovery

1 code implementation16 Feb 2022 Zhaocheng Zhu, Chence Shi, Zuobai Zhang, Shengchao Liu, Minghao Xu, Xinyu Yuan, Yangtian Zhang, Junkun Chen, Huiyu Cai, Jiarui Lu, Chang Ma, Runcheng Liu, Louis-Pascal Xhonneux, Meng Qu, Jian Tang

However, lacking domain knowledge (e. g., which tasks to work on), standard benchmarks and data preprocessing pipelines are the main obstacles for machine learning researchers to work in this domain.

Drug Discovery Molecular Property Prediction

Generative Coarse-Graining of Molecular Conformations

no code implementations28 Jan 2022 Wujie Wang, Minkai Xu, Chen Cai, Benjamin Kurt Miller, Tess Smidt, Yusu Wang, Jian Tang, Rafael Gómez-Bombarelli

Coarse-graining (CG) of molecular simulations simplifies the particle representation by grouping selected atoms into pseudo-beads and therefore drastically accelerates simulation.

LegoDNN: Block-grained Scaling of Deep Neural Networks for Mobile Vision

no code implementations18 Dec 2021 Rui Han, Qinglong Zhang, Chi Harold Liu, Guoren Wang, Jian Tang, Lydia Y. Chen

The prior art sheds light on exploring the accuracy-resource tradeoff by scaling the model sizes in accordance to resource dynamics.

Knowledge Distillation Model Compression +1

Make A Long Image Short: Adaptive Token Length for Vision Transformers

no code implementations3 Dec 2021 Yichen Zhu, Yuqin Zhu, Jie Du, Yi Wang, Zhicai Ou, Feifei Feng, Jian Tang

The TLA enables the ReViT to process the image with the minimum sufficient number of tokens during inference.

Action Recognition Image Classification

Predicting Molecular Conformation via Dynamic Graph Score Matching

no code implementations NeurIPS 2021 Shitong Luo, Chence Shi, Minkai Xu, Jian Tang

However, these non-bonded atoms may be proximal to each other in 3D space, and modeling their interactions is of crucial importance to accurately determine molecular conformations, especially for large molecules and multi-molecular complexes.

Training BatchNorm Only in Neural Architecture Search and Beyond

no code implementations1 Dec 2021 Yichen Zhu, Jie Du, Yuqin Zhu, Yi Wang, Zhicai Ou, Feifei Feng, Jian Tang

Critically, there is no effort to understand 1) why training BatchNorm only can find the perform-well architectures with the reduced supernet-training time, and 2) what is the difference between the train-BN-only supernet and the standard-train supernet.

Fairness Neural Architecture Search

Joint Modeling of Visual Objects and Relations for Scene Graph Generation

no code implementations NeurIPS 2021 Minghao Xu, Meng Qu, Bingbing Ni, Jian Tang

We further propose an efficient and effective algorithm for inference based on mean-field variational inference, in which we first provide a warm initialization by independently predicting the objects and their relations according to the current model, followed by a few iterations of relational reasoning.

Graph Generation Knowledge Graph Embedding +4

How to transfer algorithmic reasoning knowledge to learn new algorithms?

no code implementations NeurIPS 2021 Louis-Pascal A. C. Xhonneux, Andreea Deac, Petar Velickovic, Jian Tang

Due to the fundamental differences between algorithmic reasoning knowledge and feature extractors such as used in Computer Vision or NLP, we hypothesise that standard transfer techniques will not be sufficient to achieve systematic generalisation.

Learning to Execute Multi-Task Learning

CATRO: Channel Pruning via Class-Aware Trace Ratio Optimization

no code implementations21 Oct 2021 Wenzheng Hu, Ning Liu, Zhengping Che, Mingyang Li, Jian Tang, ChangShui Zhang, Jianqiang Wang

Deep convolutional neural networks are shown to be overkill with high parametric and computational redundancy in many application scenarios, and an increasing number of works have explored model pruning to obtain lightweight and efficient networks.

Neural Algorithmic Reasoners are Implicit Planners

no code implementations NeurIPS 2021 Andreea Deac, Petar Veličković, Ognjen Milinković, Pierre-Luc Bacon, Jian Tang, Mladen Nikolić

We find that prior approaches either assume that the environment is provided in such a tabular form -- which is highly restrictive -- or infer "local neighbourhoods" of states to run value iteration over -- for which we discover an algorithmic bottleneck effect.

Self-Supervised Learning

Multi-task Learning with Domain Knowledge for Molecular Property Prediction

no code implementations NeurIPS Workshop AI4Scien 2021 Shengchao Liu, Meng Qu, Zuobai Zhang, Huiyu Cai, Jian Tang

In this paper, we study multi-task learning for molecule property prediction in a different setting, where a relation graph between different tasks is available.

Drug Discovery Molecular Property Prediction +2

Human Pose Transfer with Augmented Disentangled Feature Consistency

no code implementations23 Jul 2021 Kun Wu, Chengxiang Yin, Zhengping Che, Bo Jiang, Jian Tang, Zheng Guan, Gangyi Ding

Deep generative models have made great progress in synthesizing images with arbitrary human poses and transferring poses of one person to others.

Data Augmentation Pose Transfer

Unsupervised Path Representation Learning with Curriculum Negative Sampling

1 code implementation17 Jun 2021 Sean Bin Yang, Chenjuan Guo, Jilin Hu, Jian Tang, Bin Yang

In the global view, PIM distinguishes the representations of the input paths from those of the negative paths.

Recommendation Systems Representation Learning

Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction

1 code implementation NeurIPS 2021 Zhaocheng Zhu, Zuobai Zhang, Louis-Pascal Xhonneux, Jian Tang

To further improve the capacity of the path formulation, we propose the Neural Bellman-Ford Network (NBFNet), a general graph neural network framework that solves the path formulation with learned operators in the generalized Bellman-Ford algorithm.

Inductive Relation Prediction Link Prediction

Self-supervised Graph-level Representation Learning with Local and Global Structure

1 code implementation8 Jun 2021 Minghao Xu, Hang Wang, Bingbing Ni, Hongyu Guo, Jian Tang

This paper studies unsupervised/self-supervised whole-graph representation learning, which is critical in many tasks such as molecule properties prediction in drug and material discovery.

Graph Representation Learning

Non-Autoregressive Electron Redistribution Modeling for Reaction Prediction

no code implementations8 Jun 2021 Hangrui Bi, Hengyi Wang, Chence Shi, Connor Coley, Jian Tang, Hongyu Guo

Reliably predicting the products of chemical reactions presents a fundamental challenge in synthetic chemistry.

An End-to-End Framework for Molecular Conformation Generation via Bilevel Programming

1 code implementation15 May 2021 Minkai Xu, Wujie Wang, Shitong Luo, Chence Shi, Yoshua Bengio, Rafael Gomez-Bombarelli, Jian Tang

Specifically, the molecular graph is first encoded in a latent space, and then the 3D structures are generated by solving a principled bilevel optimization program.

Bilevel Optimization

Learning Gradient Fields for Molecular Conformation Generation

5 code implementations9 May 2021 Chence Shi, Shitong Luo, Minkai Xu, Jian Tang

We study a fundamental problem in computational chemistry known as molecular conformation generation, trying to predict stable 3D structures from 2D molecular graphs.

Translation

Learning Neural Generative Dynamics for Molecular Conformation Generation

3 code implementations ICLR 2021 Minkai Xu, Shitong Luo, Yoshua Bengio, Jian Peng, Jian Tang

Inspired by the recent progress in deep generative models, in this paper, we propose a novel probabilistic framework to generate valid and diverse conformations given a molecular graph.

Lottery Ticket Preserves Weight Correlation: Is It Desirable or Not?

no code implementations19 Feb 2021 Ning Liu, Geng Yuan, Zhengping Che, Xuan Shen, Xiaolong Ma, Qing Jin, Jian Ren, Jian Tang, Sijia Liu, Yanzhi Wang

In deep model compression, the recent finding "Lottery Ticket Hypothesis" (LTH) (Frankle & Carbin, 2018) pointed out that there could exist a winning ticket (i. e., a properly pruned sub-network together with original weight initialization) that can achieve competitive performance than the original dense network.

Model Compression

Hierarchical Graph Attention Network for Few-Shot Visual-Semantic Learning

no code implementations ICCV 2021 Chengxiang Yin, Kun Wu, Zhengping Che, Bo Jiang, Zhiyuan Xu, Jian Tang

Deep learning has made tremendous success in computer vision, natural language processing and even visual-semantic learning, which requires a huge amount of labeled training data.

Graph Attention Image Captioning +2

GraphSAD: Learning Graph Representations with Structure-Attribute Disentanglement

no code implementations1 Jan 2021 Minghao Xu, Hang Wang, Bingbing Ni, Wenjun Zhang, Jian Tang

We propose to disentangle graph structure and node attributes into two distinct sets of representations, and such disentanglement can be done in either the input or the embedding space.

Disentanglement Graph Classification

Decoupled Greedy Learning of Graph Neural Networks

no code implementations1 Jan 2021 Yewen Wang, Jian Tang, Yizhou Sun, Guy Wolf

We empirically analyse our proposed DGL-GNN model, and demonstrate its effectiveness and superior efficiency through a range of experiments.

Non-autoregressive electron flow generation for reaction prediction

no code implementations16 Dec 2020 Hangrui Bi, Hengyi Wang, Chence Shi, Jian Tang

Our model achieves both an order of magnitude lower inference latency, with state-of-the-art top-1 accuracy and comparable performance on Top-K sampling.

Utilising Graph Machine Learning within Drug Discovery and Development

no code implementations9 Dec 2020 Thomas Gaudelet, Ben Day, Arian R. Jamasb, Jyothish Soman, Cristian Regep, Gertrude Liu, Jeremy B. R. Hayter, Richard Vickers, Charles Roberts, Jian Tang, David Roblin, Tom L. Blundell, Michael M. Bronstein, Jake P. Taylor-King

Graph Machine Learning (GML) is receiving growing interest within the pharmaceutical and biotechnology industries for its ability to model biomolecular structures, the functional relationships between them, and integrate multi-omic datasets - amongst other data types.

Drug Discovery

Towards Generalized Implementation of Wasserstein Distance in GANs

1 code implementation7 Dec 2020 Minkai Xu, Zhiming Zhou, Guansong Lu, Jian Tang, Weinan Zhang, Yong Yu

Wasserstein GANs (WGANs), built upon the Kantorovich-Rubinstein (KR) duality of Wasserstein distance, is one of the most theoretically sound GAN models.

Robust Unsupervised Video Anomaly Detection by Multi-Path Frame Prediction

no code implementations5 Nov 2020 Xuanzhao Wang, Zhengping Che, Bo Jiang, Ning Xiao, Ke Yang, Jian Tang, Jieping Ye, Jingyu Wang, Qi Qi

In this paper, we propose a novel and robust unsupervised video anomaly detection method by frame prediction with proper design which is more in line with the characteristics of surveillance videos.

Anomaly Detection Frame

Fast Object Detection with Latticed Multi-Scale Feature Fusion

no code implementations5 Nov 2020 Yue Shi, Bo Jiang, Zhengping Che, Jian Tang

In this work, we present a novel module, the Fluff block, to alleviate drawbacks of current multi-scale fusion methods and facilitate multi-scale object detection.

Real-Time Object Detection

DAIS: Automatic Channel Pruning via Differentiable Annealing Indicator Search

no code implementations4 Nov 2020 Yushuo Guan, Ning Liu, Pengyu Zhao, Zhengping Che, Kaigui Bian, Yanzhi Wang, Jian Tang

The convolutional neural network has achieved great success in fulfilling computer vision tasks despite large computation overhead against efficient deployment.

Neural Architecture Search

XLVIN: eXecuted Latent Value Iteration Nets

no code implementations25 Oct 2020 Andreea Deac, Petar Veličković, Ognjen Milinković, Pierre-Luc Bacon, Jian Tang, Mladen Nikolić

Value Iteration Networks (VINs) have emerged as a popular method to incorporate planning algorithms within deep reinforcement learning, enabling performance improvements on tasks requiring long-range reasoning and understanding of environment dynamics.

Graph Representation Learning reinforcement-learning +1

Towards Interpretable Natural Language Understanding with Explanations as Latent Variables

1 code implementation NeurIPS 2020 Wangchunshu Zhou, Jinyi Hu, HANLIN ZHANG, Xiaodan Liang, Maosong Sun, Chenyan Xiong, Jian Tang

In this paper, we develop a general framework for interpretable natural language understanding that requires only a small set of human annotated explanations for training.

Explanation Generation Natural Language Understanding

Predicting Infectiousness for Proactive Contact Tracing

1 code implementation ICLR 2021 Yoshua Bengio, Prateek Gupta, Tegan Maharaj, Nasim Rahaman, Martin Weiss, Tristan Deleu, Eilif Muller, Meng Qu, Victor Schmidt, Pierre-Luc St-Charles, Hannah Alsdurf, Olexa Bilanuik, David Buckeridge, Gáetan Marceau Caron, Pierre-Luc Carrier, Joumana Ghosn, Satya Ortiz-Gagne, Chris Pal, Irina Rish, Bernhard Schölkopf, Abhinav Sharma, Jian Tang, Andrew Williams

Predictions are used to provide personalized recommendations to the individual via an app, as well as to send anonymized messages to the individual's contacts, who use this information to better predict their own infectiousness, an approach we call proactive contact tracing (PCT).

Iterative Graph Self-Distillation

no code implementations23 Oct 2020 HANLIN ZHANG, Shuai Lin, Weiyang Liu, Pan Zhou, Jian Tang, Xiaodan Liang, Eric P. Xing

How to discriminatively vectorize graphs is a fundamental challenge that attracts increasing attentions in recent years.

Contrastive Learning Graph Learning +1

Knowledge Transfer in Multi-Task Deep Reinforcement Learning for Continuous Control

1 code implementation NeurIPS 2020 Zhiyuan Xu, Kun Wu, Zhengping Che, Jian Tang, Jieping Ye

While Deep Reinforcement Learning (DRL) has emerged as a promising approach to many complex tasks, it remains challenging to train a single DRL agent that is capable of undertaking multiple different continuous control tasks.

Continuous Control online learning +2

RNNLogic: Learning Logic Rules for Reasoning on Knowledge Graphs

2 code implementations ICLR 2021 Meng Qu, Junkun Chen, Louis-Pascal Xhonneux, Yoshua Bengio, Jian Tang

Then in the E-step, we select a set of high-quality rules from all generated rules with both the rule generator and reasoning predictor via posterior inference; and in the M-step, the rule generator is updated with the rules selected in the E-step.

Knowledge Graphs

Emergence of Chern insulating states in non-Magic angle twisted bilayer graphene

no code implementations8 Oct 2020 Cheng Shen, Jianghua Ying, Le Liu, Jianpeng Liu, Na Li, Shuopei Wang, Jian Tang, Yanchong Zhao, Yanbang Chu, Kenji Watanabe, Takashi Taniguchi, Rong Yang, Dongxia Shi, Fanming Qu, Li Lu, Wei Yang, Guangyu Zhang

For {\theta}=1. 25{\deg}, we observe an emergence of topological insulating states at hole side with a sequence of Chern number |C|=4-|v|, where v is the number of electrons (holes) in moir\'e unite cell.

Mesoscale and Nanoscale Physics Materials Science

Graph neural induction of value iteration

no code implementations26 Sep 2020 Andreea Deac, Pierre-Luc Bacon, Jian Tang

Previously, such planning components have been incorporated through a neural network that partially aligns with the computational graph of value iteration.

reinforcement-learning

Differentiable Feature Aggregation Search for Knowledge Distillation

no code implementations ECCV 2020 Yushuo Guan, Pengyu Zhao, Bingxuan Wang, Yuanxing Zhang, Cong Yao, Kaigui Bian, Jian Tang

To tackle with both the efficiency and the effectiveness of knowledge distillation, we introduce the feature aggregation to imitate the multi-teacher distillation in the single-teacher distillation framework by extracting informative supervision from multiple teacher feature maps.

Knowledge Distillation Model Compression +1

GRADE: Graph Dynamic Embedding

no code implementations16 Jul 2020 Simeon Spasov, Alessandro Di Stefano, Pietro Lio, Jian Tang

At each time step link generation is performed by first assigning node membership from a distribution over the communities, and then sampling a neighbor from a distribution over the nodes for the assigned community.

Community Detection Dynamic Community Detection +3

Few-shot Relation Extraction via Bayesian Meta-learning on Relation Graphs

1 code implementation5 Jul 2020 Meng Qu, Tianyu Gao, Louis-Pascal A. C. Xhonneux, Jian Tang

To more effectively generalize to new relations, in this paper we study the relationships between different relations and propose to leverage a global relation graph.

Meta-Learning Relation Extraction

Graph Policy Network for Transferable Active Learning on Graphs

1 code implementation NeurIPS 2020 Shengding Hu, Zheng Xiong, Meng Qu, Xingdi Yuan, Marc-Alexandre Côté, Zhiyuan Liu, Jian Tang

Graph neural networks (GNNs) have been attracting increasing popularity due to their simplicity and effectiveness in a variety of fields.

Active Learning

Domain Conditioned Adaptation Network

1 code implementation14 May 2020 Shuang Li, Chi Harold Liu, Qiuxia Lin, Binhui Xie, Zhengming Ding, Gao Huang, Jian Tang

Most existing deep DA models only focus on aligning feature representations of task-specific layers across domains while integrating a totally shared convolutional architecture for source and target.

Domain Adaptation

An Image Enhancing Pattern-based Sparsity for Real-time Inference on Mobile Devices

no code implementations ECCV 2020 Xiaolong Ma, Wei Niu, Tianyun Zhang, Sijia Liu, Sheng Lin, Hongjia Li, Xiang Chen, Jian Tang, Kaisheng Ma, Bin Ren, Yanzhi Wang

Weight pruning has been widely acknowledged as a straightforward and effective method to eliminate redundancy in Deep Neural Networks (DNN), thereby achieving acceleration on various platforms.

Code Generation

Continuous Graph Neural Networks

1 code implementation ICML 2020 Louis-Pascal A. C. Xhonneux, Meng Qu, Jian Tang

The key idea is how to characterise the continuous dynamics of node representations, i. e. the derivatives of node representations, w. r. t.

Node Classification

Deep geometric knowledge distillation with graphs

1 code implementation8 Nov 2019 Carlos Lassance, Myriam Bontonou, Ghouthi Boukli Hacene, Vincent Gripon, Jian Tang, Antonio Ortega

Specifically we introduce a graph-based RKD method, in which graphs are used to capture the geometry of latent spaces.

Knowledge Distillation

GraphMix: Improved Training of GNNs for Semi-Supervised Learning

1 code implementation25 Sep 2019 Vikas Verma, Meng Qu, Kenji Kawaguchi, Alex Lamb, Yoshua Bengio, Juho Kannala, Jian Tang

We present GraphMix, a regularization method for Graph Neural Network based semi-supervised object classification, whereby we propose to train a fully-connected network jointly with the graph neural network via parameter sharing and interpolation-based regularization.

Generalization Bounds Graph Attention +1

Transfer Active Learning For Graph Neural Networks

no code implementations25 Sep 2019 Shengding Hu, Meng Qu, Zhiyuan Liu, Jian Tang

Moreover, we also studied how to learn a universal policy for labeling nodes on graphs with multiple training graphs and then transfer the learned policy to unseen graphs.

Active Learning Node Classification +1

Empowering Graph Representation Learning with Paired Training and Graph Co-Attention

no code implementations25 Sep 2019 Andreea Deac, Yu-Hsiang Huang, Petar Velickovic, Pietro Lio, Jian Tang

Through many recent advances in graph representation learning, performance achieved on tasks involving graph-structured data has substantially increased in recent years---mostly on tasks involving node-level predictions.

Graph Classification Graph Regression +1

GraphMix: Regularized Training of Graph Neural Networks for Semi-Supervised Learning

no code implementations25 Sep 2019 Vikas Verma, Meng Qu, Alex Lamb, Yoshua Bengio, Juho Kannala, Jian Tang

We present GraphMix, a regularization technique for Graph Neural Network based semi-supervised object classification, leveraging the recent advances in the regularization of classical deep neural networks.

Structural Robustness for Deep Learning Architectures

no code implementations11 Sep 2019 Carlos Lassance, Vincent Gripon, Jian Tang, Antonio Ortega

Deep Networks have been shown to provide state-of-the-art performance in many machine learning challenges.

PCONV: The Missing but Desirable Sparsity in DNN Weight Pruning for Real-time Execution on Mobile Devices

no code implementations6 Sep 2019 Xiaolong Ma, Fu-Ming Guo, Wei Niu, Xue Lin, Jian Tang, Kaisheng Ma, Bin Ren, Yanzhi Wang

Model compression techniques on Deep Neural Network (DNN) have been widely acknowledged as an effective way to achieve acceleration on a variety of platforms, and DNN weight pruning is a straightforward and effective method.

Model Compression

Data-Driven Approach to Encoding and Decoding 3-D Crystal Structures

1 code implementation3 Sep 2019 Jordan Hoffmann, Louis Maestrati, Yoshihide Sawada, Jian Tang, Jean Michel Sellier, Yoshua Bengio

We present a method to encode and decode the position of atoms in 3-D molecules from a dataset of nearly 50, 000 stable crystal unit cells that vary from containing 1 to over 100 atoms.

Drug Discovery Text Generation

An End-to-End Neighborhood-based Interaction Model for Knowledge-enhanced Recommendation

1 code implementation12 Aug 2019 Yanru Qu, Ting Bai, Wei-Nan Zhang, Jian-Yun Nie, Jian Tang

This paper studies graph-based recommendation, where an interaction graph is constructed from historical records and is lever-aged to alleviate data sparsity and cold start problems.

Click-Through Rate Prediction Knowledge Graphs

InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization

3 code implementations ICLR 2020 Fan-Yun Sun, Jordan Hoffmann, Vikas Verma, Jian Tang

There are also some recent methods based on language models (e. g. graph2vec) but they tend to only consider certain substructures (e. g. subtrees) as graph representatives.

Graph Classification Molecular Property Prediction +1

Weakly-supervised Knowledge Graph Alignment with Adversarial Learning

no code implementations ICLR 2019 Meng Qu, Jian Tang, Yoshua Bengio

Therefore, in this paper we propose to study aligning knowledge graphs in fully-unsupervised or weakly-supervised fashion, i. e., without or with only a few aligned triplets.

Knowledge Graphs

AutoCompress: An Automatic DNN Structured Pruning Framework for Ultra-High Compression Rates

no code implementations6 Jul 2019 Ning Liu, Xiaolong Ma, Zhiyuan Xu, Yanzhi Wang, Jian Tang, Jieping Ye

This work proposes AutoCompress, an automatic structured pruning framework with the following key performance improvements: (i) effectively incorporate the combination of structured pruning schemes in the automatic process; (ii) adopt the state-of-art ADMM-based structured weight pruning as the core algorithm, and propose an innovative additional purification step for further weight reduction without accuracy loss; and (iii) develop effective heuristic search method enhanced by experience-based guided search, replacing the prior deep reinforcement learning technique which has underlying incompatibility with the target pruning problem.

Model Compression

Ekar: An Explainable Method for Knowledge Aware Recommendation

2 code implementations22 Jun 2019 Weiping Song, Zhijian Duan, Ziqing Yang, Hao Zhu, Ming Zhang, Jian Tang

Recently, a variety of methods have been developed for this problem, which generally try to learn effective representations of users and items and then match items to users according to their representations.

Knowledge-Aware Recommendation Knowledge Graphs +1

Probabilistic Logic Neural Networks for Reasoning

2 code implementations NeurIPS 2019 Meng Qu, Jian Tang

In the E-step, a knowledge graph embedding model is used for inferring the missing triplets, while in the M-step, the weights of logic rules are updated based on both the observed and predicted triplets.

Knowledge Graph Embedding Knowledge Graphs

vGraph: A Generative Model for Joint Community Detection and Node Representation Learning

1 code implementation NeurIPS 2019 Fan-Yun Sun, Meng Qu, Jordan Hoffmann, Chin-wei Huang, Jian Tang

Experimental results on multiple real-world graphs show that vGraph is very effective in both community detection and node representation learning, outperforming many competitive baselines in both tasks.

Community Detection Representation Learning +1

Learning Powerful Policies by Using Consistent Dynamics Model

1 code implementation11 Jun 2019 Shagun Sodhani, Anirudh Goyal, Tristan Deleu, Yoshua Bengio, Sergey Levine, Jian Tang

There is enough evidence that humans build a model of the environment, not only by observing the environment but also by interacting with the environment.

Atari Games Model-based Reinforcement Learning

DivGraphPointer: A Graph Pointer Network for Extracting Diverse Keyphrases

no code implementations19 May 2019 Zhiqing Sun, Jian Tang, Pan Du, Zhi-Hong Deng, Jian-Yun Nie

Furthermore, we propose a diversified point network to generate a set of diverse keyphrases out of the word graph in the decoding process.

Document Summarization Information Retrieval +1

GMNN: Graph Markov Neural Networks

1 code implementation15 May 2019 Meng Qu, Yoshua Bengio, Jian Tang

Statistical relational learning methods can effectively model the dependency of object labels through conditional random fields for collective classification, whereas graph neural networks learn effective object representations for classification through end-to-end training.

Classification General Classification +2

Drug-Drug Adverse Effect Prediction with Graph Co-Attention

1 code implementation2 May 2019 Andreea Deac, Yu-Hsiang Huang, Petar Veličković, Pietro Liò, Jian Tang

Complex or co-existing diseases are commonly treated using drug combinations, which can lead to higher risk of adverse side effects.

The ALOS Dataset for Advert Localization in Outdoor Scenes

no code implementations16 Apr 2019 Soumyabrata Dev, Murhaf Hossari, Matthew Nicholson, Killian McCabe, Atul Nautiyal, Clare Conran, Jian Tang, Wei Xu, François Pitié

The rapid increase in the number of online videos provides the marketing and advertising agents ample opportunities to reach out to their audience.

Frame Semantic Segmentation

Signal-to-Noise Ratio: A Robust Distance Metric for Deep Metric Learning

no code implementations CVPR 2019 Tongtong Yuan, Weihong Deng, Jian Tang, Yinan Tang, Binghui Chen

In this paper, different from the approaches on learning the loss structures, we propose a robust SNR distance metric based on Signal-to-Noise Ratio (SNR) for measuring the similarity of image pairs for deep metric learning.

Image Clustering Metric Learning +2

Progressive DNN Compression: A Key to Achieve Ultra-High Weight Pruning and Quantization Rates using ADMM

2 code implementations23 Mar 2019 Shaokai Ye, Xiaoyu Feng, Tianyun Zhang, Xiaolong Ma, Sheng Lin, Zhengang Li, Kaidi Xu, Wujie Wen, Sijia Liu, Jian Tang, Makan Fardad, Xue Lin, Yongpan Liu, Yanzhi Wang

A recent work developed a systematic frame-work of DNN weight pruning using the advanced optimization technique ADMM (Alternating Direction Methods of Multipliers), achieving one of state-of-art in weight pruning results.

Model Compression Quantization

The CASE Dataset of Candidate Spaces for Advert Implantation

no code implementations21 Mar 2019 Soumyabrata Dev, Murhaf Hossari, Matthew Nicholson, Killian McCabe, Atul Nautiyal, Clare Conran, Jian Tang, Wei Xu, François Pitié

With the advent of faster internet services and growth of multimedia content, we observe a massive growth in the number of online videos.

Semantic Segmentation

Learning Hierarchical Representations of Electronic Health Records for Clinical Outcome Prediction

no code implementations20 Mar 2019 Lu-chen Liu, Haoran Li, Zhiting Hu, Haoran Shi, Zichang Wang, Jian Tang, Ming Zhang

Our model learns hierarchical representationsof event sequences, to adaptively distinguish between short-range and long-range events, and accurately capture coretemporal dependencies.

GraphVite: A High-Performance CPU-GPU Hybrid System for Node Embedding

1 code implementation2 Mar 2019 Zhaocheng Zhu, Shizhen Xu, Meng Qu, Jian Tang

In this paper, we propose GraphVite, a high-performance CPU-GPU hybrid system for training node embeddings, by co-optimizing the algorithm and the system.

Dimensionality Reduction Knowledge Graph Embedding +3

Session-based Social Recommendation via Dynamic Graph Attention Networks

2 code implementations25 Feb 2019 Weiping Song, Zhiping Xiao, Yifan Wang, Laurent Charlin, Ming Zhang, Jian Tang

However, recommendation in online communities is a challenging problem: 1) users' interests are dynamic, and 2) users are influenced by their friends.

 Ranked #1 on Recommendation Systems on Douban (NDCG metric)

Graph Attention Recommendation Systems

Contextualized Non-local Neural Networks for Sequence Learning

no code implementations21 Nov 2018 Pengfei Liu, Shuaichen Chang, Xuanjing Huang, Jian Tang, Jackie Chi Kit Cheung

Recently, a large number of neural mechanisms and models have been proposed for sequence learning, of which self-attention, as exemplified by the Transformer model, and graph neural networks (GNNs) have attracted much attention.

General Classification Text Classification

ADNet: A Deep Network for Detecting Adverts

no code implementations9 Nov 2018 Murhaf Hossari, Soumyabrata Dev, Matthew Nicholson, Killian McCabe, Atul Nautiyal, Clare Conran, Jian Tang, Wei Xu, François Pitié

Online video advertising gives content providers the ability to deliver compelling content, reach a growing audience, and generate additional revenue from online media.

Detecting Adverts Frame

Data Poisoning Attack against Unsupervised Node Embedding Methods

no code implementations30 Oct 2018 Mingjie Sun, Jian Tang, Huichen Li, Bo Li, Chaowei Xiao, Yao Chen, Dawn Song

In this paper, we take the task of link prediction as an example, which is one of the most fundamental problems for graph analysis, and introduce a data positioning attack to node embedding methods.

Data Poisoning Link Prediction

AutoInt: Automatic Feature Interaction Learning via Self-Attentive Neural Networks

10 code implementations29 Oct 2018 Weiping Song, Chence Shi, Zhiping Xiao, Zhijian Duan, Yewen Xu, Ming Zhang, Jian Tang

Afterwards, a multi-head self-attentive neural network with residual connections is proposed to explicitly model the feature interactions in the low-dimensional space.

Click-Through Rate Prediction Recommendation Systems

Learning powerful policies and better dynamics models by encouraging consistency

no code implementations27 Sep 2018 Shagun Sodhani, Anirudh Goyal, Tristan Deleu, Yoshua Bengio, Jian Tang

Analogously, we would expect such interaction to be helpful for a learning agent while learning to model the environment dynamics.

Model-based Reinforcement Learning

StructADMM: A Systematic, High-Efficiency Framework of Structured Weight Pruning for DNNs

1 code implementation29 Jul 2018 Tianyun Zhang, Shaokai Ye, Kaiqi Zhang, Xiaolong Ma, Ning Liu, Linfeng Zhang, Jian Tang, Kaisheng Ma, Xue Lin, Makan Fardad, Yanzhi Wang

Without loss of accuracy on the AlexNet model, we achieve 2. 58X and 3. 65X average measured speedup on two GPUs, clearly outperforming the prior work.

Model Compression

DeepInf: Social Influence Prediction with Deep Learning

1 code implementation15 Jul 2018 Jiezhong Qiu, Jian Tang, Hao Ma, Yuxiao Dong, Kuansan Wang, Jie Tang

Inspired by the recent success of deep neural networks in a wide range of computing applications, we design an end-to-end framework, DeepInf, to learn users' latent feature representation for predicting social influence.

Feature Engineering Representation Learning

Adversarial Meta-Learning

no code implementations8 Jun 2018 Chengxiang Yin, Jian Tang, Zhiyuan Xu, Yanzhi Wang

Meta-learning enables a model to learn from very limited data to undertake a new task.

Meta-Learning

A Systematic DNN Weight Pruning Framework using Alternating Direction Method of Multipliers

3 code implementations ECCV 2018 Tianyun Zhang, Shaokai Ye, Kaiqi Zhang, Jian Tang, Wujie Wen, Makan Fardad, Yanzhi Wang

We first formulate the weight pruning problem of DNNs as a nonconvex optimization problem with combinatorial constraints specifying the sparsity requirements, and then adopt the ADMM framework for systematic weight pruning.

Image Classification Network Pruning

Learning the Joint Representation of Heterogeneous Temporal Events for Clinical Endpoint Prediction

1 code implementation13 Mar 2018 Lu-chen Liu, Jianhao Shen, Ming Zhang, Zichang Wang, Jian Tang

One important application is clinical endpoint prediction, which aims to predict whether a disease, a symptom or an abnormal lab test will happen in the future according to patients' history records.

Model-Free Control for Distributed Stream Data Processing using Deep Reinforcement Learning

no code implementations2 Mar 2018 Teng Li, Zhiyuan Xu, Jian Tang, Yanzhi Wang

Specifically, we, for the first time, propose to leverage emerging Deep Reinforcement Learning (DRL) for enabling model-free control in DSDPSs; and present design, implementation and evaluation of a novel and highly effective DRL-based control framework, which minimizes average end-to-end tuple processing time by jointly learning the system environment via collecting very limited runtime statistics data and making decisions under the guidance of powerful Deep Neural Networks.

online learning reinforcement-learning

Deep Reinforcement Learning for Dynamic Treatment Regimes on Medical Registry Data

no code implementations28 Jan 2018 Ning Liu, Ying Liu, Brent Logan, Zhiyuan Xu, Jian Tang, Yanzhi Wang

This paper presents the first deep reinforcement learning (DRL) framework to estimate the optimal Dynamic Treatment Regimes from observational medical data.

reinforcement-learning

Experience-driven Networking: A Deep Reinforcement Learning based Approach

no code implementations17 Jan 2018 Zhiyuan Xu, Jian Tang, Jingsong Meng, Weiyi Zhang, Yanzhi Wang, Chi Harold Liu, Dejun Yang

Modern communication networks have become very complicated and highly dynamic, which makes them hard to model, predict and control.

Continuous Control reinforcement-learning

A Systematic Analysis for State-of-the-Art 3D Lung Nodule Proposals Generation

1 code implementation9 Jan 2018 Hui Wu, Matrix Yao, Albert Hu, Gaofeng Sun, Xiaokun Yu, Jian Tang

Lung nodule proposals generation is the primary step of lung nodule detection and has received much attention in recent years .

Lung Nodule Detection

Adversarial Network Embedding

no code implementations21 Nov 2017 Quanyu Dai, Qiang Li, Jian Tang, Dan Wang

Learning low-dimensional representations of networks has proved effective in a variety of tasks such as node classification, link prediction and network visualization.

Link Prediction Network Embedding +1

An Attention-based Collaboration Framework for Multi-View Network Representation Learning

1 code implementation19 Sep 2017 Meng Qu, Jian Tang, Jingbo Shang, Xiang Ren, Ming Zhang, Jiawei Han

Existing approaches usually study networks with a single type of proximity between nodes, which defines a single view of a network.

Representation Learning

End-to-end Learning for Short Text Expansion

no code implementations30 Aug 2017 Jian Tang, Yue Wang, Kai Zheng, Qiaozhu Mei

A novel deep memory network is proposed to automatically find relevant information from a collection of longer documents and reformulate the short text through a gating mechanism.

Recommendation Systems Text Classification

A Hierarchical Framework of Cloud Resource Allocation and Power Management Using Deep Reinforcement Learning

no code implementations13 Mar 2017 Ning Liu, Zhe Li, Zhiyuan Xu, Jielong Xu, Sheng Lin, Qinru Qiu, Jian Tang, Yanzhi Wang

Automatic decision-making approaches, such as reinforcement learning (RL), have been applied to (partially) solve the resource allocation problem adaptively in the cloud computing system.

Decision Making reinforcement-learning

Theoretical Properties for Neural Networks with Weight Matrices of Low Displacement Rank

no code implementations ICML 2017 Liang Zhao, Siyu Liao, Yanzhi Wang, Zhe Li, Jian Tang, Victor Pan, Bo Yuan

Recently low displacement rank (LDR) matrices, or so-called structured matrices, have been proposed to compress large-scale neural networks.

Identity-sensitive Word Embedding through Heterogeneous Networks

no code implementations29 Nov 2016 Jian Tang, Meng Qu, Qiaozhu Mei

Based on an identity-labeled text corpora, a heterogeneous network of words and word identities is constructed to model different-levels of word co-occurrences.

Network Embedding Text Classification +2

Context-aware Natural Language Generation with Recurrent Neural Networks

1 code implementation29 Nov 2016 Jian Tang, Yifan Yang, Sam Carton, Ming Zhang, Qiaozhu Mei

This paper studied generating natural languages at particular contexts or situations.

Text Generation

Less is More: Learning Prominent and Diverse Topics for Data Summarization

no code implementations29 Nov 2016 Jian Tang, Cheng Li, Ming Zhang, Qiaozhu Mei

With this reinforced random walk as a general process embedded in classical topic models, we obtain \textit{diverse topic models} that are able to extract the most prominent and diverse topics from data.

Data Summarization Topic Models

PixelSNE: Visualizing Fast with Just Enough Precision via Pixel-Aligned Stochastic Neighbor Embedding

1 code implementation8 Nov 2016 Minjeong Kim, Minsuk Choi, Sunwoong Lee, Jian Tang, Haesun Park, Jaegul Choo

Embedding and visualizing large-scale high-dimensional data in a two-dimensional space is an important problem since such visualization can reveal deep insights out of complex data.

Visualizing Large-scale and High-dimensional Data

5 code implementations1 Feb 2016 Jian Tang, Jingzhou Liu, Ming Zhang, Qiaozhu Mei

We propose the LargeVis, a technique that first constructs an accurately approximated K-nearest neighbor graph from the data and then layouts the graph in the low-dimensional space.

graph construction

PTE: Predictive Text Embedding through Large-scale Heterogeneous Text Networks

1 code implementation2 Aug 2015 Jian Tang, Meng Qu, Qiaozhu Mei

One possible reason is that these text embedding methods learn the representation of text in a fully unsupervised way, without leveraging the labeled information available for the task.

Representation Learning

LINE: Large-scale Information Network Embedding

8 code implementations12 Mar 2015 Jian Tang, Meng Qu, Mingzhe Wang, Ming Zhang, Jun Yan, Qiaozhu Mei

This paper studies the problem of embedding very large information networks into low-dimensional vector spaces, which is useful in many tasks such as visualization, node classification, and link prediction.

Graph Embedding Link Prediction +2

"Look Ma, No Hands!" A Parameter-Free Topic Model

no code implementations10 Sep 2014 Jian Tang, Ming Zhang, Qiaozhu Mei

We show that the new parameter can be further eliminated by two parameter-free treatments: either by monitoring the diversity among the discovered topics or by a weak supervision from users in the form of an exemplar topic.

Model Selection Topic Models

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