Jian Tang

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

Huiyu Cai

PhD - Université de Montréal

huiyu.cai@mila.quebec

Collaborating researcher

Farzaneh Heidari

PhD - Université de Montréal

Principal supervisor :

Guillaume Rabusseau

Jerry Lu

PhD - Université de Montréal

Stephen Lu

Research Intern - McGill University

stephen.lu@mila.quebec

Shentong Mo

Collaborating researcher - Carnegie Mellon University

Chence Shi

PhD - Université de Montréal

Sophie Xhonneux

PhD - Université de Montréal

Principal supervisor :

Gauthier Gidel

lpxhonneux@gmail.com

Minghao Xu

Collaborating researcher

Xinyu Yuan

PhD - Université de Montréal

xinyu.yuan@mila.quebec

Zhihao Zhan

PhD - Université de Montréal

Zuobai Zhang

PhD - Université de Montréal

zhaocheng.zhu@umontreal.ca

Jianan Zhao

PhD - Université de Montréal

PhD - Université de Montréal

Publications

Deep Equilibrium Models For Algorithmic Reasoning

Sophie Xhonneux

Yu He

Andreea Deac

Gauthier Gidel

In this blogpost we discuss the idea of teaching neural networks to reach fixed points when reasoning. Specifically, on the algorithmic reas… (see more)oning benchmark CLRS the current neural networks are told the number of reasoning steps they need. While a quick fix is to add a termination network that predicts when to stop, a much more salient inductive bias is that the neural network shouldn't change it's answer any further once the answer is correct, i.e. it should reach a fixed point. This is supported by denotational semantics, which tells us that while loops that terminate are the minimum fixed points of a function. We implement this idea with the help of deep equilibrium models and discuss several hurdles one encounters along the way. We show on several algorithms from the CLRS benchmark the partial success of this approach and the difficulty in making it work robustly across all algorithms.

2024-02-16

ICLR.cc/2024/BlogPosts (accepted)

In-Context Learning Can Re-learn Forbidden Tasks

Sophie Xhonneux

David Dobre

Gauthier Gidel

Dhanya Sridhar

Despite significant investment into safety training, large language models (LLMs) deployed in the real world still suffer from numerous vuln… (see more)erabilities. One perspective on LLM safety training is that it algorithmically forbids the model from answering toxic or harmful queries. To assess the effectiveness of safety training, in this work, we study forbidden tasks, i.e., tasks the model is designed to refuse to answer. Specifically, we investigate whether in-context learning (ICL) can be used to re-learn forbidden tasks despite the explicit fine-tuning of the model to refuse them. We first examine a toy example of refusing sentiment classification to demonstrate the problem. Then, we use ICL on a model fine-tuned to refuse to summarise made-up news articles. Finally, we investigate whether ICL can undo safety training, which could represent a major security risk. For the safety task, we look at Vicuna-7B, Starling-7B, and Llama2-7B. We show that the attack works out-of-the-box on Starling-7B and Vicuna-7B but fails on Llama2-7B. Finally, we propose an ICL attack that uses the chat template tokens like a prompt injection attack to achieve a better attack success rate on Vicuna-7B and Starling-7B. Trigger Warning: the appendix contains LLM-generated text with violence, suicide, and misinformation.

2024-02-08

ArXiv (preprint)

arxiv.org

Machine Learning Informed Diagnosis for Congenital Heart Disease in Large Claims Data Source

Ariane Marelli

Chao Li

Aihua Liu

Hanh Nguyen

Harry Moroz

James M. Brophy

Liming Guo

2024-02-01

JACC: Advances (published)

Unsupervised Discovery of Steerable Factors When Graph Deep Generative Models Are Entangled

Shengchao Liu

Chengpeng Wang

Jiarui Lu

Weili Nie

Hanchen Wang

Zhuoxinran Li

Bolei Zhou

2024-01-30

TMLR (accepted)

Real-time monitoring for the next core-collapse supernova in JUNO

Angel Abusleme

Thomas Adam

Shakeel Ahmad

Rizwan Ahmed

Sebastiano Aiello

Muhammad Akram

Abid Aleem

Fengpeng An

Qi An

Giuseppe Andronico

Nikolay Anfimov

Vito Antonelli

Tatiana Antoshkina

Burin Asavapibhop

João Pedro Athayde Marcondes de André

Didier Auguste

Weidong Bai

Nikita Balashov

Wander Baldini

Andrea Barresi … (see 480 more)

Davide Basilico

Eric Baussan

Marco Bellato

Marco Beretta

Antonio Bergnoli

Daniel Bick

Lukas Bieger

Svetlana Biktemerova

Thilo Birkenfeld

Iwan Morton-blake

David Blum

Simon Blyth

Anastasia Bolshakova

Mathieu Bongrand

Clément Bordereau

Dominique Breton

Augusto Brigatti

Riccardo Brugnera

Riccardo Bruno

Antonio Budano

Jose Busto

Anatael Cabrera

Barbara Caccianiga

Hao Cai

Xiao Cai

Yanke Cai

Z. Cai

Stéphane Callier

Antonio Cammi

Agustin Campeny

C. Cao

Guofu Cao

Jun Cao

Rossella Caruso

C. Cerna

Vanessa Cerrone

Chi Chan

Jinfan Chang

Yun Chang

Auttakit Chatrabhuti

Chao Chen

Guoming Chen

Pingping Chen

Shaomin Chen

Yixue Chen

Yu Chen

Zhangming Chen

Zhiyuan Chen

Zikang Chen

Jie Cheng

Yaping Cheng

Yuanyuan Zhang

Alexander Chepurnov

Alexey Chetverikov

Davide Chiesa

Pietro Chimenti

Yen-Ting Chin

Ziliang Chu

Artem Chukanov

Gérard Claverie

Catia Clementi

Barbara Clerbaux

Marta Colomer Molla

Selma Conforti Di Lorenzo

Alberto Coppi

Daniele Corti

Simon Csakli

Flavio Dal Corso

Olivia Dalager

Jaydeep Datta

C. Taille

Zhi Deng

Ziyan Deng

Xiaoyu Ding

Xuefeng Ding

Yayun Ding

Bayu Dirgantara

Carsten Dittrich

Sergey Dmitrievsky

Tadeas Dohnal

Dmitry Dolzhikov

Georgy Donchenko

Jianmeng Dong

Evgeny Doroshkevich

Wei Dou

Marcos Dracos

Frédéric Druillole

Ran Du

S. X. Du

K. Dugas

Stefano Dusini

Hongyue Duyang

J. Eck

Timo Enqvist

Andrea Fabbri

Ulrike Fahrendholz

Lei Fan

Jian Fang

Wen Fang

Marco Fargetta

Dmitry Fedoseev

Zhengyong Fei

Li-Cheng Feng

Qichun Feng

Federico Ferraro

Amélie Fournier

H. Gan

Feng Gao

Alberto Garfagnini

Arsenii Gavrikov

Marco Giammarchi

Nunzio Giudice

Maxim Gonchar

G. Gong

Hui Gong

Yuri Gornushkin

A. Gottel

Marco Grassi

Maxim Gromov

Vasily Gromov

Minghao Gu

X. Gu

Yunting Gu

M. Guan

Yuduo Guan

Nunzio Guardone

Cong Guo

Wanlei Guo

Xinheng Guo

Caren Hagner

Ran Han

Yang Han

Miao He

W. He

Tobias Heinz

Patrick Hellmuth

Yue-kun Heng

Rafael Herrera

Y. Hor

Shaojing Hou

Yee Hsiung

Bei-Zhen Hu

Hang Hu

Jianrun Hu

Jun Hu

Shouyang Hu

Tao Hu

Yuxiang Hu

Zhuojun Hu

Guihong Huang

Hanxiong Huang

Jinhao Huang

Jun-Hao Huang

Kaixuan Huang

Wenhao Huang

Xinting Huang

X. T. Huang

Yongbo Huang

Jiaqi Hui

Lei Huo

Wenju Huo

Cédric Huss

Safeer Hussain

Leonard Imbert

Ara Ioannisian

Roberto Isocrate

Arshak Jafar

Beatrice Jelmini

Ignacio Jeria

Xiaolu Ji

Huihui Jia

Junji Jia

Siyu Jian

Cailian Jiang

Di Jiang

Wei Jiang

Xiaoshan Jiang

X. Jing

Cécile Jollet

Philipp Kampmann

Li Kang

Rebin Karaparambil

Narine Kazarian

Ali Khan

Amina Khatun

Khanchai Khosonthongkee

Denis Korablev

K. Kouzakov

Alexey Krasnoperov

Sergey Kuleshov

Nikolay Kutovskiy

Loïc Labit

Tobias Lachenmaier

Cecilia Landini

Sébastien Leblanc

Victor Lebrin

Frederic Lefevre

Rui Li

Rupert Leitner

Jason Leung

Demin Li

Fei Li

Fule Li

Gaosong Li

Huiling Li

Jiajun Li

Mengzhao Li

Min Li

Nan Li

Qingjiang Li

Ruhui Li

Ruiting Lei

Shanfeng Li

Tao Li

Teng Li

Weidong Li

Weiguo Li

Xiaomei Li

Xiaonan Li

Xinglong Li

Yi Li

Yichen Li

Yufeng Li

Zhaohan Li

Zhibing Li

Ziyuan Li

Zonghui Li

Hao Liang

Jiaming Yan

Ayut Limphirat

G. Lin

Shengxin Lin

Tao Lin

Jiajie Ling

Xin Ling

Ivano Lippi

Caimei Liu

Yang Liu

Fengcheng Liu

Haidong Liu

Hao Liu

Hongbang Liu

Hongjuan Liu

Hongtao Liu

Hui Liu

Jianglai Liu

Jia-xing Liu

Jinchang Liu

Min Liu

Qian Liu

Q. Liu

Runxuan Liu

Sheng Liu

Shubin Liu

Shulin Liu

Xiaowei Liu

Xiwen Liu

Xue (Steve) Liu

Yankai Liu

Zhen Liu

Alexey Lokhov

Paolo Lombardi

Claudio Lombardo

Kai Loo

Chuan Lu

Haoqi Lu

Jingbin Lu

Junguang Lu

Peizhi Lu

Shuxiang Lu

Xianguo Lu

Bayarto Lubsandorzhiev

Sultim Lubsandorzhiev

Livia Ludhova

Arslan Lukanov

Daibin Luo

F. Luo

Guang Luo

Jianyi Luo

Shu Luo

Wuming Luo

Xiaojie Luo

Vladimir Lyashuk

B. Ma

Bing Ma

R. Q. Ma

Si Ma

Xiaoyan Ma

Xubo Ma

Jihane Maalmi

Marco Magoni

Jingyu Mai

Yury Malyshkin

Roberto Carlos Mandujano

Fabio Mantovani

Xin Mao

Yajun Mao

S. Mari

F. Marini

Agnese Martini

Matthias Mayer

Davit Mayilyan

Ints Mednieks

Yu Meng

Anita Meraviglia

Anselmo Meregaglia

Emanuela Meroni

David J. Meyhofer

Lino Miramonti

Nikhil Mohan

Michele Montuschi

Axel Muller

M. Nastasi

Dmitry V. Naumov

Elena Naumova

Diana Navas-Nicolas

Igor Nemchenok

Minh Thuan Nguyen Thi

Alexey Nikolaev

F. Ning

Zhe Ning

Hiroshi Nunokawa

Lothar Oberauer

Juan Pedro Ochoa-Ricoux

Alexander Olshevskiy

Domizia Orestano

Fausto Ortica

Rainer Othegraven

A. Paoloni

Sergio Parmeggiano

Y. P. Pei

Luca Pelicci

Anguo Peng

Yu Peng

Yuefeng Peng

Z-R Peng

Frédéric Perrot

P. Petitjean

Fabrizio Petrucci

Oliver Pilarczyk

Luis Felipe Piñeres Rico

Artyom Popov

Pascal Poussot

Ezio Previtali

Fazhi Qi

M. Qi

Xiaohui Qi

Sen Qian

X. Qian

Zhen Qian

Hao-xue Qiao

Zhonghua Qin

S. Qiu

Manhao Qu

Z. Qu

Gioacchino Ranucci

Reem Rasheed

A. Re

Abdel Rebii

Mariia Redchuk

Bin Ren

Jie Ren

Barbara Ricci

Komkrit Rientong

Mariam Rifai

Mathieu Roche

Narongkiat Rodphai

Aldo M. Romani

Bedřich Roskovec

X. Ruan

Arseniy Rybnikov

Andrey Sadovsky

Paolo Saggese

Deshan Sandanayake

Anut Sangka

G. Sava

Utane Sawangwit

Michaela Schever

Cédric Schwab

Konstantin Schweizer

Alexandr Selyunin

Andrea Serafini

M. Settimo

V. Sharov

Arina Shaydurova

Jingyan Shi

Yanan Shi

Vitaly Shutov

Andrey Sidorenkov

Fedor Šimkovic

Apeksha Singhal

Chiara Sirignano

Jaruchit Siripak

Monica Sisti

Mikhail Smirnov

Oleg Smirnov

Thiago Sogo-Bezerra

Sergey Sokolov

Julanan Songwadhana

Boonrucksar Soonthornthum

Albert Sotnikov

Ondvrej vSr'amek

Warintorn Sreethawong

Achim Stahl

Luca Stanco

Konstantin Stankevich

Hans Steiger

Jochen Steinmann

Tobias Sterr

M. Stock

Virginia Strati

Alexander Studenikin

Aoqi Su

Jun Su

Shifeng Sun

Xilei Sun

Yongjie Sun Sun

Yongzhao Sun

Zhengyang Sun

Narumon Suwonjandee

Michal Szelezniak

Akira Takenaka

Qiang Tang

Quan Tang

Xiao Tang

Vidhya Thara Hariharan

Eric Theisen

Alexander Tietzsch

Igor Tkachev

Tomas Tmej

M. Torri

Francesco Tortorici

K. Treskov

Andrea Triossi

Riccardo Triozzi

Wladyslaw Trzaska

Y. Tung

Cristina Tuve

Nikita Ushakov

Vadim Vedin

Carlo Venettacci

Giuseppe Verde

Maxim Vialkov

Benoit Viaud

Cornelius Moritz Vollbrecht

Katharina von Sturm

Vit Vorobel

Dmitriy Voronin

Lucia Votano

Pablo Walker

Caishen Wang

Chung-Hsiang Wang

En Wang

Guoli Wang

Jian Wang

Jun Wang

Li Wang

Lucinda W. Wang

Meng Wang

Ruiguang Wang

Siguang Wang

W. Wang

Wenshuai Wang

Xi Wang

Xiangyue Wang

Yangfu Wang

Yaoguang Wang

Yi Xing Wang

Yifang Wang

Yuanqing Wang

Yuyi Wang

Zhe Wang

Zheng Wang

Zhimin Wang

Apimook Watcharangkool

Wei Wei

Wenlu Wei

Yadong Wei

Yuehuan Wei

The core-collapse supernova (CCSN) is considered one of the most energetic astrophysical events in the universe. The early and prompt detect… (see more)ion of neutrinos before (pre-SN) and during the supernova (SN) burst presents a unique opportunity for multi-messenger observations of CCSN events. In this study, we describe the monitoring concept and present the sensitivity of the system to pre-SN and SN neutrinos at the Jiangmen Underground Neutrino Observatory (JUNO), a 20 kton liquid scintillator detector currently under construction in South China. The real-time monitoring system is designed to ensure both prompt alert speed and comprehensive coverage of progenitor stars. It incorporates prompt monitors on the electronic board as well as online monitors at the data acquisition stage. Assuming a false alert rate of 1 per year, this monitoring system exhibits sensitivity to pre-SN neutrinos up to a distance of approximately 1.6 (0.9) kiloparsecs and SN neutrinos up to about 370 (360) kiloparsecs for a progenitor mass of 30 solar masses, considering both normal and inverted mass ordering scenarios. The pointing ability of the CCSN is evaluated by analyzing the accumulated event anisotropy of inverse beta decay interactions from pre-SN or SN neutrinos. This, along with the early alert, can play a crucial role in facilitating follow-up multi-messenger observations of the next galactic or nearby extragalactic CCSN.

2024-01-25

Journal of Cosmology and Astroparticle Physics (published)

arxiv.org

Evaluating Representation Learning on the Protein Structure Universe

Arian Rokkum Jamasb

Alex Morehead

Chaitanya K. Joshi

Zuobai Zhang

Kieran Didi

Simon V Mathis

Charles Harris

Jianlin Cheng

Pietro Lio

Tom Leon Blundell

2024-01-16

ICLR.cc/2024/Conference (poster)

Str2Str: A Score-based Framework for Zero-shot Protein Conformation Sampling

Jiarui Lu

Bozitao Zhong

Zuobai Zhang

2024-01-16

ICLR.cc/2024/Conference (poster)

Towards Foundation Models for Knowledge Graph Reasoning

Mikhail Galkin

Xinyu Yuan

Hesham Mostafa

Zhaocheng Zhu

Foundation models in language and vision have the ability to run inference on any textual and visual inputs thanks to the transferable repre… (see more)sentations such as a vocabulary of tokens in language. Knowledge graphs (KGs) have different entity and relation vocabularies that generally do not overlap. The key challenge of designing foundation models on KGs is to learn such transferable representations that enable inference on any graph with arbitrary entity and relation vocabularies. In this work, we make a step towards such foundation models and present ULTRA, an approach for learning universal and transferable graph representations. ULTRA builds relational representations as a function conditioned on their interactions. Such a conditioning strategy allows a pre-trained ULTRA model to inductively generalize to any unseen KG with any relation vocabulary and to be fine-tuned on any graph. Conducting link prediction experiments on 57 different KGs, we find that the zero-shot inductive inference performance of a single pre-trained ULTRA model on unseen graphs of various sizes is often on par or better than strong baselines trained on specific graphs. Fine-tuning further boosts the performance.

2024-01-16

ICLR.cc/2024/Conference (poster)

Towards Foundational Models for Molecular Learning on Large-Scale Multi-Task Datasets

Dominique Beaini

Shenyang Huang

Joao Alex Cunha

Zhiyi Li

Gabriela Moisescu-Pareja

Oleksandr Dymov

Samuel Maddrell-Mander

Callum McLean

Frederik Wenkel

Luis Müller

Jama Hussein Mohamud

Ali Parviz

Michael Craig

Michał Koziarski

Jiarui Lu

Zhaocheng Zhu

Cristian Gabellini

Kerstin Klaser

Josef Dean

Cas Wognum … (see 15 more)

Maciej Sypetkowski

Guillaume Rabusseau

Reihaneh Rabbany

Christopher Morris

Ioannis Koutis

Mirco Ravanelli

Guy Wolf

Prudencio Tossou

Hadrien Mary

Therence Bois

Andrew William Fitzgibbon

Blazej Banaszewski

Chad Martin

Dominic Masters

Recently, pre-trained foundation models have enabled significant advancements in multiple fields. In molecular machine learning, however, wh… (see more)ere datasets are often hand-curated, and hence typically small, the lack of datasets with labeled features, and codebases to manage those datasets, has hindered the development of foundation models. In this work, we present seven novel datasets categorized by size into three distinct categories: ToyMix, LargeMix and UltraLarge. These datasets push the boundaries in both the scale and the diversity of supervised labels for molecular learning. They cover nearly 100 million molecules and over 3000 sparsely defined tasks, totaling more than 13 billion individual labels of both quantum and biological nature. In comparison, our datasets contain 300 times more data points than the widely used OGB-LSC PCQM4Mv2 dataset, and 13 times more than the quantum-only QM1B dataset. In addition, to support the development of foundational models based on our proposed datasets, we present the Graphium graph machine learning library which simplifies the process of building and training molecular machine learning models for multi-task and multi-level molecular datasets. Finally, we present a range of baseline results as a starting point of multi-task and multi-level training on these datasets. Empirically, we observe that performance on low-resource biological datasets show improvement by also training on large amounts of quantum data. This indicates that there may be potential in multi-task and multi-level training of a foundation model and fine-tuning it to resource-constrained downstream tasks. The Graphium library is publicly available on Github and the dataset links are available in Part 1 and Part 2.

2024-01-16

ICLR.cc/2024/Conference (poster)

CO emission predictions in municipal solid waste incineration based on reduced depth features and long short-term memory optimization

Runyu Zhang

Heng Xia

Xiaotong Pan

Wen Yu

JunFei Qiao

2024-01-08

Neural computing & applications (Print) (published)

CATRO: Channel Pruning via Class-Aware Trace Ratio Optimization

Wenzheng Hu

Ning Liu

Zhengping Che

Mingyang Li

Changshui Zhang

Jianqiang Wang

Deep convolutional neural networks are shown to be overkill with high parametric and computational redundancy in many application scenarios,… (see more) and an increasing number of works have explored model pruning to obtain lightweight and efficient networks. However, most existing pruning approaches are driven by empirical heuristics and rarely consider the joint impact of channels, leading to unguaranteed and suboptimal performance. In this article, we propose a novel channel pruning method via class-aware trace ratio optimization (CATRO) to reduce the computational burden and accelerate the model inference. Utilizing class information from a few samples, CATRO measures the joint impact of multiple channels by feature space discriminations and consolidates the layerwise impact of preserved channels. By formulating channel pruning as a submodular set function maximization problem, CATRO solves it efficiently via a two-stage greedy iterative optimization procedure. More importantly, we present theoretical justifications on convergence of CATRO and performance of pruned networks. Experimental results demonstrate that CATRO achieves higher accuracy with similar computation cost or lower computation cost with similar accuracy than other state-of-the-art channel pruning algorithms. In addition, because of its class-aware property, CATRO is suitable to prune efficient networks adaptively for various classification subtasks, enhancing handy deployment and usage of deep networks in real-world applications.

2024-01-01

IEEE Trans. Neural Networks Learn. Syst. (published)

arxiv.org

Hybrid Simulator-Based Mechanism and Data-Driven for Multidemand Dioxin Emissions Intelligent Prediction in the MSWI Process

Heng Xia

Wen Yu

JunFei Qiao

2024-01-01

IEEE transactions on industrial electronics (1982. Print) (published)