Jian Tang

Biographie

Jian Tang est professeur agrégé au département de sciences de la décision de HEC. Il est aussi professeur associé au département informatique et recherche opérationnelle (DIRO) de l'Université de Montréal et un membre académique principal à Mila – Institut québécois d’intelligence artificielle. Il est titulaire d'une chaire de recherche en IA Canada-CIFAR et le fondateur de BioGeometry, une entreprise en démarrage spécialisée dans l'IA générative pour la découverte d'anticorps. Ses principaux domaines de recherche sont les modèles génératifs profonds, l'apprentissage automatique des graphes et leurs applications à la découverte de médicaments. Il est un leader international dans le domaine de l'apprentissage automatique des graphes, et son travail représentatif sur l'apprentissage de la représentation des nœuds, LINE, a été largement reconnu et cité plus de 5 000 fois. Il a également réalisé de nombreux travaux pionniers sur l'IA pour la découverte de médicaments, notamment le premier cadre d'apprentissage automatique à source ouverte pour la découverte de médicaments, TorchDrug et TorchProtein.

Étudiants actuels

Huiyu Cai

Doctorat - UdeM

Doctorat - UdeM

Superviseur⋅e principal⋅e :

Xixian Liu

Doctorat - Université de Montréal

Jiarui Lu

Doctorat - UdeM

Github

Chence Shi

Doctorat - UdeM

Sophie Xhonneux

Doctorat - UdeM

Superviseur⋅e principal⋅e :

Gauthier Gidel

Xinyu Yuan

Doctorat - UdeM

Github

Zhihao Zhan

Doctorat - UdeM

Doctorat - UdeM

Doctorat - HEC

Jianan Zhao

Doctorat - UdeM

Github

Publications

In-Context Learning Can Re-learn Forbidden Tasks

David Dobre

Despite significant investment into safety training, large language models (LLMs) deployed in the real world still suffer from numerous vuln… (voir plus)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.

2024-02-07

ArXiv (prépublication)

arxiv.org

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

Ariane J. Marelli

Chao Li

Aihua Liu

Hanh Nguyen

Harry Moroz

James M. Brophy

Liming Guo

David L. Buckeridge

Archer Y. Yang

Yue Li

2024-01-31

JACC: Advances (publié)

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

2024-01-29

TMLR (accepté)

Evaluating Representation Learning on the Protein Structure Universe

Arian R. Jamasb

Alex Morehead

Chaitanya K. Joshi

Zuobai Zhang

Kieran Didi

Simon Mathis

Charles Harris

Jianlin Cheng

Pietro Lio

Tom L. Blundell

We introduce ProteinWorkshop, a comprehensive benchmark suite for representation learning on protein structures with Geometric Graph Neural … (voir plus)Networks. We consider large-scale pre-training and downstream tasks on both experimental and predicted structures to enable the systematic evaluation of the quality of the learned structural representation and their usefulness in capturing functional relationships for downstream tasks. We find that: (1) large-scale pretraining on AlphaFold structures and auxiliary tasks consistently improve the performance of both rotation-invariant and equivariant GNNs, and (2) more expressive equivariant GNNs benefit from pretraining to a greater extent compared to invariant models. We aim to establish a common ground for the machine learning and computational biology communities to rigorously compare and advance protein structure representation learning. Our open-source codebase reduces the barrier to entry for working with large protein structure datasets by providing: (1) storage-efficient dataloaders for large-scale structural databases including AlphaFoldDB and ESM Atlas, as well as (2) utilities for constructing new tasks from the entire PDB. ProteinWorkshop is available at: github.com/a-r-j/ProteinWorkshop.

2024-01-15

ICLR.cc/2024/Conference (poster)

Str2str: A Score-Based Framework for Zero-Shot Protein Conformation Sampling

Jiarui Lu

Bozitao Zhong

Zuobai Zhang

The dynamic nature of proteins is crucial for determining their biological functions and properties, for which Monte Carlo (MC) and molecula… (voir plus)r dynamics (MD) simulations stand as predominant tools to study such phenomena. By utilizing empirically derived force fields, MC or MD simulations explore the conformational space through numerically evolving the system via Markov chain or Newtonian mechanics. However, the high-energy barrier of the force fields can hamper the exploration of both methods by the rare event, resulting in inadequately sampled ensemble without exhaustive running. Existing learning-based approaches perform direct sampling yet heavily rely on target-specific simulation data for training, which suffers from high data acquisition cost and poor generalizability. Inspired by simulated annealing, we propose Str2Str, a novel structure-to-structure translation framework capable of zero-shot conformation sampling with roto-translation equivariant property. Our method leverages an amortized denoising score matching objective trained on general crystal structures and has no reliance on simulation data during both training and inference. Experimental results across several benchmarking protein systems demonstrate that Str2Str outperforms previous state-of-the-art generative structure prediction models and can be orders of magnitude faster compared to long MD simulations. Our open-source implementation is available at https://github.com/lujiarui/Str2Str

2024-01-15

ICLR.cc/2024/Conference (poster)

Towards Foundation Models for Knowledge Graph Reasoning

Hesham Mostafa

Foundation models in language and vision have the ability to run inference on any textual and visual inputs thanks to the transferable repre… (voir plus)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.

2024-01-15

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

Jama Hussein Mohamud

Michael Craig

Cristian Gabellini

Kerstin Klasers

Josef Dean

Cas Wognum … (voir 15 de plus)

Maciej Sypetkowski

Ioannis Koutis

Hadrien Mary

Therence Bois

Andrew Fitzgibbon

Błażej Banaszewski

Chad Martin

Dominic Masters

Recently, pre-trained foundation models have shown significant advancements in multiple fields. However, the lack of datasets with labeled f… (voir plus)eatures and codebases has hindered the development of a supervised foundation model for molecular tasks. Here, we have carefully curated seven datasets specifically tailored for node- and graph-level prediction tasks to facilitate supervised learning on molecules. Moreover, to support the development of multi-task learning on our proposed datasets, we created the Graphium graph machine learning library. Our dataset collection encompasses two distinct categories. Firstly, the TOYMIX category modifies three small existing datasets with additional data for multi-task learning. Secondly, the LARGEMIX category includes four large-scale datasets with 344M graph-level data points and 409M node-level data points from ∼5M unique molecules. Finally, the ultra-large dataset contains 2,210M graph-level data points and 2,031M node-level data points coming from 86M molecules. Hence our datasets represent an order of magnitude increase in data volume compared to other 2D-GNN datasets. In addition, recognizing that molecule-related tasks often span multiple levels, we have designed our library to explicitly support multi-tasking, offering a diverse range of multi-level representations, i.e., representations at the graph, node, edge, and node-pair level. We equipped the library with an extensive collection of models and features to cover different levels of molecule analysis. By combining our curated datasets with this versatile library, we aim to accelerate the development of molecule foundation models. Datasets and code are available at https://github.com/datamol-io/graphium.

2024-01-15

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

2024-01-07

Neural computing & applications (Print) (publié)

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,… (voir plus) 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.

2023-12-31

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

arxiv.org

A Foundation Model for Zero-shot Logical Query Reasoning

Mikhail Galkin

Jincheng Zhou

Bruno Ribeiro

Zhaocheng Zhu

Complex logical query answering (CLQA) in knowledge graphs (KGs) goes beyond simple KG completion and aims at answering compositional querie… (voir plus)s comprised of multiple projections and logical operations. Existing CLQA methods that learn parameters bound to certain entity or relation vocabularies can only be applied to the graph they are trained on which requires substantial training time before being deployed on a new graph. Here we present UltraQuery, the first foundation model for inductive reasoning that can zero-shot answer logical queries on any KG. The core idea of UltraQuery is to derive both projections and logical operations as vocabulary-independent functions which generalize to new entities and relations in any KG. With the projection operation initialized from a pre-trained inductive KG reasoning model, UltraQuery can solve CLQA on any KG after finetuning on a single dataset. Experimenting on 23 datasets, UltraQuery in the zero-shot inference mode shows competitive or better query answering performance than best available baselines and sets a new state of the art on 15 of them.

2023-12-31

NeurIPS (publié)

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

Heng Xia

Wen Yu

JunFei Qiao

2023-12-31

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

Multi-objective PSO semi-supervised random forest method for dioxin soft sensor

Wen Xu

Heng Xia

Wen Yu

JunFei Qiao

2023-12-31

Eng. Appl. Artif. Intell. (publié)