Portrait of Jian Tang

Jian Tang

Core Academic Member

tangjian@mila.quebec

Canada CIFAR AI Chair

Associate Professor, HEC Montréal, Department of Decision Sciences

Adjunct Professor, Université de Montréal, Department of Computer Science and Operations Research

Founder, BioGeometry

Research Topics

AI for Science

Computational Biology

Generative Models

Graph Neural Networks

Large Language Models (LLM)

Molecular Modeling

Biography

Jian Tang is an Associate professor at HEC's Department of Decision Sciences. He is also an Adjunct professor at the Department of Computer Science and Operations Research at University of Montreal and a Core Academic member at Mila - Quebec AI Institute. He is a Canada CIFAR AI Chair and the Founder of BioGeometry, an AI startup that focuses on generative AI for antibody discovery. Tang’s main research interests are deep generative models and graph machine learning, and their applications to drug discovery. He is an international leader in graph machine learning, and LINE, his node representation method, has been widely recognized and cited more than five thousand times. He has also done pioneering work on AI for drug discovery, such as developing the first open-source machine learning frameworks for drug discovery, TorchDrug and TorchProtein.

Current Students

PhD - Université de Montréal

huiyu.cai@mila.quebec

Farzana Heidari

PhD - Université de Montréal

Principal supervisor :

Guillaume Rabusseau

farzaneh.heidari@mila.quebec

PhD - Université de Montréal

xixian.liu@mila.quebec

PhD - Université de Montréal

jiarui.lu@mila.quebec

Sophie Xhonneux

PhD - Université de Montréal

Principal supervisor :

lpxhonneux@gmail.com

Collaborating researcher - Wuhan University

jinxi.yang@mila.quebec

PhD - Université de Montréal

xinyu.yuan@mila.quebec

PhD - Université de Montréal

zhihao.zhan@mila.quebec

PhD - Université de Montréal

zuobai.zhang@mila.quebec

PhD - HEC Montréal

ya-shi.zhang@mila.quebec

PhD - Université de Montréal

jianan.zhao@mila.quebec

Publications

GMNN: Graph Markov Neural Networks

This paper studies semi-supervised object classification in relational data, which is a fundamental problem in relational data modeling. The… (see more) problem has been extensively studied in the literature of both statistical relational learning (e.g. relational Markov networks) and graph neural networks (e.g. graph convolutional networks). 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. In this paper, we propose the Graph Markov Neural Network (GMNN) that combines the advantages of both worlds. A GMNN models the joint distribution of object labels with a conditional random field, which can be effectively trained with the variational EM algorithm. In the E-step, one graph neural network learns effective object representations for approximating the posterior distributions of object labels. In the M-step, another graph neural network is used to model the local label dependency. Experiments on object classification, link classification, and unsupervised node representation learning show that GMNN achieves state-of-the-art results.

2019-05-23

Proceedings of the 36th International Conference on Machine Learning (published)

proceedings.mlr.press

Session-Based Social Recommendation via Dynamic Graph Attention Networks

Zhiping Xiao

Yifan Wang

Laurent Charlin

Ming Zhang

Online communities such as Facebook and Twitter are enormously popular and have become an essential part of the daily life of many of their … (see more)users. Through these platforms, users can discover and create information that others will then consume. In that context, recommending relevant information to users becomes critical for viability. However, recommendation in online communities is a challenging problem: 1) users' interests are dynamic, and 2) users are influenced by their friends. Moreover, the influencers may be context-dependent. That is, different friends may be relied upon for different topics. Modeling both signals is therefore essential for recommendations. We propose a recommender system for online communities based on a dynamic-graph-attention neural network. We model dynamic user behaviors with a recurrent neural network, and context-dependent social influence with a graph-attention neural network, which dynamically infers the influencers based on users' current interests. The whole model can be efficiently fit on large-scale data. Experimental results on several real-world data sets demonstrate the effectiveness of our proposed approach over several competitive baselines including state-of-the-art models.

2019-01-29

Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining (published)

Learning powerful policies and better dynamics models by encouraging consistency

2018-09-26

(published)