Jian Tang

farzaneh.heidari@mila.quebec

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

huiyu.cai@mila.quebec

Doctorat - UdeM

Superviseur⋅e principal⋅e :

Guillaume Rabusseau

Xixian Liu

Doctorat - Université de Montréal

xixian.liu@mila.quebec

Jiarui Lu

Doctorat - UdeM

jiarui.lu@mila.quebec

Doctorat - UdeM

Superviseur⋅e principal⋅e :

Gauthier Gidel

lpxhonneux@gmail.com

Jinxi Yang

Collaborateur·rice de recherche - Wuhan University

jinxi.yang@mila.quebec

Xinyu Yuan

Doctorat - UdeM

xinyu.yuan@mila.quebec

Zhihao Zhan

Doctorat - UdeM

zhihao.zhan@mila.quebec

Zuobai Zhang

Doctorat - UdeM

zuobai.zhang@mila.quebec

Doctorat - HEC

ya-shi.zhang@mila.quebec

Jianan Zhao

Doctorat - UdeM

jianan.zhao@mila.quebec

Publications

FusionRetro: Molecule Representation Fusion via Reaction Graph for Retrosynthetic Planning

Songtao Liu

Zhengkai Tu

Minkai Xu

Zuobai Zhang

Peilin Zhao

Rex Ying

Lu Lin

Dinghao Wu

Retrosynthetic planning is a fundamental problem in drug discovery and organic chemistry, which aims to ﬁnd a complete multi-step syntheti… (voir plus)c route from a set of starting materials to the target molecule, determining crucial process ﬂow in chemical production. Existing approaches combine single-step retrosynthesis models and search algorithms to ﬁnd synthetic routes. However, these approaches generally consider the two pieces in a decoupled manner, taking only the product as the input to predict the reactants per planning step and largely ignoring the important context information from other intermediates along the synthetic route. In this work, we perform a series of experiments to identify the limitations of this decoupled view and propose a novel retrosynthesis framework that also exploits context information for retrosynthetic planning. We view synthetic routes as reaction graphs, and propose to incorporate the context by three principled steps: encode molecules into embeddings, aggregate information over routes, and readout to predict reactants. The whole framework can be efﬁciently optimized in an end-to-end fashion. Comprehensive experiments show that by fusing in context information over routes, our model sig-niﬁcantly improves the performance of retrosyn-thetic planning over baselines that are not context-aware, especially for long synthetic routes.

2022-12-31

(publié)

www.semanticscholar.org

Debiasing Graph Neural Networks via Learning Disentangled Causal Substructure

Shaohua Fan

Xiao Wang

Yanhu Mo

Chuan Shi

Most Graph Neural Networks (GNNs) predict the labels of unseen graphs by learning the correlation between the input graphs and labels. Howev… (voir plus)er, by presenting a graph classification investigation on the training graphs with severe bias, surprisingly, we discover that GNNs always tend to explore the spurious correlations to make decision, even if the causal correlation always exists. This implies that existing GNNs trained on such biased datasets will suffer from poor generalization capability. By analyzing this problem in a causal view, we find that disentangling and decorrelating the causal and bias latent variables from the biased graphs are both crucial for debiasing. Inspiring by this, we propose a general disentangled GNN framework to learn the causal substructure and bias substructure, respectively. Particularly, we design a parameterized edge mask generator to explicitly split the input graph into causal and bias subgraphs. Then two GNN modules supervised by causal/bias-aware loss functions respectively are trained to encode causal and bias subgraphs into their corresponding representations. With the disentangled representations, we synthesize the counterfactual unbiased training samples to further decorrelate causal and bias variables. Moreover, to better benchmark the severe bias problem, we construct three new graph datasets, which have controllable bias degrees and are easier to visualize and explain. Experimental results well demonstrate that our approach achieves superior generalization performance over existing baselines. Furthermore, owing to the learned edge mask, the proposed model has appealing interpretability and transferability. Code and data are available at: https://github.com/googlebaba/DisC.

2022-11-28

Conference on Neural Information Processing Systems (Accept)

High-Order Pooling for Graph Neural Networks with Tensor Decomposition

Chenqing Hua

Guillaume Rabusseau

Graph Neural Networks (GNNs) are attracting growing attention due to their effectiveness and flexibility in modeling a variety of graph-stru… (voir plus)ctured data. Exiting GNN architectures usually adopt simple pooling operations (eg. sum, average, max) when aggregating messages from a local neighborhood for updating node representation or pooling node representations from the entire graph to compute the graph representation. Though simple and effective, these linear operations do not model high-order non-linear interactions among nodes. We propose the Tensorized Graph Neural Network (tGNN), a highly expressive GNN architecture relying on tensor decomposition to model high-order non-linear node interactions. tGNN leverages the symmetric CP decomposition to efficiently parameterize permutation-invariant multilinear maps for modeling node interactions. Theoretical and empirical analysis on both node and graph classification tasks show the superiority of tGNN over competitive baselines. In particular, tGNN achieves the most solid results on two OGB node classification datasets and one OGB graph classification dataset.

2022-11-28

Neural Information Processing Systems (Accept)

Inductive Logical Query Answering in Knowledge Graphs

Mikhail Galkin

Zhaocheng Zhu

Hongyu Ren

Formulating and answering logical queries is a standard communication interface for knowledge graphs (KGs). Alleviating the notorious incomp… (voir plus)leteness of real-world KGs, neural methods achieved impressive results in link prediction and complex query answering tasks by learning representations of entities, relations, and queries. Still, most existing query answering methods rely on transductive entity embeddings and cannot generalize to KGs containing new entities without retraining the entity embeddings. In this work, we study the inductive query answering task where inference is performed on a graph containing new entities with queries over both seen and unseen entities. To this end, we devise two mechanisms leveraging inductive node and relational structure representations powered by graph neural networks (GNNs). Experimentally, we show that inductive models are able to perform logical reasoning at inference time over unseen nodes generalizing to graphs up to 500% larger than training ones. Exploring the efficiency--effectiveness trade-off, we find the inductive relational structure representation method generally achieves higher performance, while the inductive node representation method is able to answer complex queries in the inference-only regime without any training on queries and scales to graphs of millions of nodes. Code is available at https://github.com/DeepGraphLearning/InductiveQE.

2022-11-28

Conference on Neural Information Processing Systems (Accept)

PEER: A Comprehensive and Multi-Task Benchmark for Protein Sequence Understanding

We are now witnessing significant progress of deep learning methods in a variety of tasks (or datasets) of proteins. However, there is a lac… (voir plus)k of a standard benchmark to evaluate the performance of different methods, which hinders the progress of deep learning in this field. In this paper, we propose such a benchmark called PEER, a comprehensive and multi-task benchmark for Protein sEquence undERstanding. PEER provides a set of diverse protein understanding tasks including protein function prediction, protein localization prediction, protein structure prediction, protein-protein interaction prediction, and protein-ligand interaction prediction. We evaluate different types of sequence-based methods for each task including traditional feature engineering approaches, different sequence encoding methods as well as large-scale pre-trained protein language models. In addition, we also investigate the performance of these methods under the multi-task learning setting. Experimental results show that large-scale pre-trained protein language models achieve the best performance for most individual tasks, and jointly training multiple tasks further boosts the performance. The datasets and source codes of this benchmark are all available at https://github.com/DeepGraphLearning/PEER_Benchmark

2022-11-28

Conference on Neural Information Processing Systems (Accept)

GraphCG: Unsupervised Discovery of Steerable Factors in Graphs

Shengchao Liu

Chengpeng Wang

Weili Nie

Hanchen Wang

Jiarui Lu

Bolei Zhou

Deep generative models have been extensively explored recently, especially for the graph data such as molecular graphs and point clouds. Yet… (voir plus), much less investigation has been carried out on understanding the learned latent space of deep graph generative models. Such understandings can open up a unified perspective and provide guidelines for essential tasks like controllable generation. In this paper, we first examine the representation space of the recent deep generative model trained for graph data, observing that the learned representation space is not perfectly disentangled. Based on this observation, we then propose an unsupervised method called GraphCG, which is model-agnostic and task-agnostic for discovering steerable factors in graph data. Specifically, GraphCG learns the semantic-rich directions via maximizing the corresponding mutual information, where the edited graph along the same direction will possess certain steerable factors. We conduct experiments on two types of graph data, molecular graphs and point clouds. Both the quantitative and qualitative results show the effectiveness of GraphCG for discovering steerable factors. The code will be public in the near future.

2022-11-21

NeurIPS.cc/2022/Workshop/GLFrontiers (accepté)

Flaky Performances when Pretraining on Relational Databases

Shengchao Liu

David Vázquez

Pierre-Andre Noel

2022-11-08

ArXiv (prépublication)

arxiv.org

Deep generative molecular design reshapes drug discovery

Xiangxiang Zeng

Yi Wang

Yuan Luo

Seung-gu Kang

Felice C. Lightstone

Evandro F. Fang

Wendy Cornell

Ruth Nussinov

Feixiong Cheng

2022-10-26

Cell Reports Medicine (publié)

Implications of Topological Imbalance for Representation Learning on Biomedical Knowledge Graphs

Stephen Bonner

Ufuk Kirik

Ola Engkvist

Ian P Barrett

Adoption of recently developed methods from machine learning has given rise to creation of drug-discovery knowledge graphs (KG) that utilize… (voir plus) the interconnected nature of the domain. Graph-based modelling of the data, combined with KG embedding (KGE) methods, are promising as they provide a more intuitive representation and are suitable for inference tasks such as predicting missing links. One common application is to produce ranked lists of genes for a given disease, where the rank is based on the perceived likelihood of association between the gene and the disease. It is thus critical that these predictions are not only pertinent but also biologically meaningful. However, KGs can be biased either directly due to the underlying data sources that are integrated or due to modeling choices in the construction of the graph, one consequence of which is that certain entities can get topologically overrepresented. We demonstrate the effect of these inherent structural imbalances, resulting in densely-connected entities being highly ranked no matter the context. We provide support for this observation across different datasets, models as well as predictive tasks. Further, we present various graph perturbation experiments which yield more support to the observation that KGE models can be more influenced by the frequency of entities rather than any biological information encoded within the relations. Our results highlight the importance of data modeling choices, and emphasizes the need for practitioners to be mindful of these issues when interpreting model outputs and during KG composition.

2022-07-25

Briefings in Bioinformatics (inconnu)

arxiv.org

Flaky Performances when Pre-Training on Relational Databases with a Plan for Future Characterization Efforts

Shengchao Liu

David Vázquez

Pierre-Andre Noel

We explore the downstream task performances for graph neural network (GNN) self-supervised learning (SSL) methods trained on subgraphs extra… (voir plus)cted from relational databases (RDBs). Intu-itively, this joint use of SSL and GNNs allows us to leverage more of the available data, which could translate to better results. However, while we observe positive transfer in some cases, others showed systematic performance degradation, including some spectacular ones. We hypothesize a mechanism that could explain this behaviour and draft the plan for future work testing it by characterizing how much relevant information different strategies can (theoretically and/or empirically) extract from (synthetic and/or real) RDBs.

2022-07-21

ICML.cc/2022/Workshop/Pre-Training (inconnu)

Generative Coarse-Graining of Molecular Conformations

Wujie Wang

Minkai Xu

Chen Cai

Benjamin K Miller

Tess Smidt

Yusu Wang

Rafael Gomez-Bombarelli

Coarse-graining (CG) of molecular simulations simplifies the particle representation by grouping selected atoms into pseudo-beads and drasti… (voir plus)cally accelerates simulation. However, such CG procedure induces information losses, which makes accurate backmapping, i.e., restoring fine-grained (FG) coordinates from CG coordinates, a long-standing challenge. Inspired by the recent progress in generative models and equivariant networks, we propose a novel model that rigorously embeds the vital probabilistic nature and geometric consistency requirements of the backmapping transformation. Our model encodes the FG uncertainties into an invariant latent space and decodes them back to FG geometries via equivariant convolutions. To standardize the evaluation of this domain, we provide three comprehensive benchmarks based on molecular dynamics trajectories. Experiments show that our approach always recovers more realistic structures and outperforms existing data-driven methods with a significant margin.

2022-07-18

ICML (Accept for Short Presentation)

proceedings.mlr.press

Neural-Symbolic Models for Logical Queries on Knowledge Graphs

Answering complex first-order logic (FOL) queries on knowledge graphs is a fundamental task for multi-hop reasoning. Traditional symbolic me… (voir plus)thods traverse a complete knowledge graph to extract the answers, which provides good interpretation for each step. Recent neural methods learn geometric embeddings for complex queries. These methods can generalize to incomplete knowledge graphs, but their reasoning process is hard to interpret. In this paper, we propose Graph Neural Network Query Executor (GNN-QE), a neural-symbolic model that enjoys the advantages of both worlds. GNN-QE decomposes a complex FOL query into relation projections and logical operations over fuzzy sets, which provides interpretability for intermediate variables. To reason about the missing links, GNN-QE adapts a graph neural network from knowledge graph completion to execute the relation projections, and models the logical operations with product fuzzy logic. Experiments on 3 datasets show that GNN-QE significantly improves over previous state-of-the-art models in answering FOL queries. Meanwhile, GNN-QE can predict the number of answers without explicit supervision, and provide visualizations for intermediate variables.

2022-07-18

International Conference on Machine Learning (Accept for Short Presentation)