Qitian Wu (吴齐天)

Postdoc at Broad Institute of MIT and Harvard

wuqitian [AT] broadinstitute.org

Github | Google Scholar | DBLP | ResearchGate

Orcid | Twitter | Medium | Zhihu



Bio

Qitian is currently a postdoctoral fellow of Eric and Wendy Schmidt Center at Broad Institute of MIT and Harvard. Prior to this, he finished the PhD in Computer Science from Shanghai Jiao Tong University (SJTU), Before that, he achieved the Bachelor (Microelectronics, Mathematics) and Master (Computer Science) degrees from SJTU, and worked as research intern at Tencent WeChat, Amazon Web Service and BioMap.

His research interest predominantly revolves around machine learning foundations and applications. On the foundation side, he builds theoretically principled and practically useful methodology, particularly for learning with complex structures and distribution shifts. He also explores the intersection with interdisciplinary areas such as biomedical sciences and recommender systems, and sought inspirations from physics. He is the recipients of Microsoft PhD Fellowship, Baidu PhD Fellowship and Scholar Star at SJTU.

Research Summary

My research generally aims at improving and broadening the capabilities of AI models to complex structured data. My recent works unfold under two learning settings, i.e., closed-world and open-world hypothesis, along which my works explore the methodology for representation and generalization challenges.

I am always open for collaborations, and if you are interested, feel free to have a chat.

Publications

The most recent works can be found on Google Scholar.

DIFFormer: Scalable (Graph) Transformers Induced by Energy Constrained Diffusion

Qitian Wu, Chenxiao Yang, Wentao Zhao, Yixuan He, David Wipf and Junchi Yan

International Conference on Learning Representations (ICLR) 2023 oral presentation, ranking among top 0.5%

Summary: We propose a geometric diffusion framework with energy constraints and show its solution aligns with widely used attention networks, upon which we propose diffusion-based Transformers.

NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classification

Qitian Wu, Wentao Zhao, Zenan Li, David Wipf and Junchi Yan

Advances in Neural Information Processing Systems (NeurIPS) 2022 spotlight presentation

Summary: We propose a scalable graph Transformer with efficient all-pair message passing achieved in O(N) complexity. The global attention over 2M nodes only requires 4GB memory.

Handling Distribution Shifts on Graphs: An Invariance Perspective

Qitian Wu, Hengrui Zhang, Junchi Yan and David Wipf

International Conference on Learning Representations (ICLR) 2022

Summary: We formulate out-of-distribution generalization on graphs and discuss how to leverage (causal) invariance principle for handling graph-based distribution shifts.

Learning Divergence Fields for Shift-Robust Message Passing

Qitian Wu, Fan Nie, Chenxiao Yang and Junchi Yan

International Conference on Machine Learning (ICML) 2024

Graph Out-of-Distribution Generalization via Causal Intervention

Qitian Wu, Fan Nie, Chenxiao Yang, Tianyi Bao and Junchi Yan

The Web Conference (WWW) 2024 oral presentation

SGFormer: Simplifying and Empowering Transformers for Large-Graph Representations

Qitian Wu, Wentao Zhao, Chenxiao Yang, Hengrui Zhang, Fan Nie, Haitian Jiang, Yatao Bian and Junchi Yan

Advances in Neural Information Processing Systems (NeurIPS) 2023

Summary: We propose an efficient Transformer that only uses one-layer global attention and significantly reduces computation cost for large-graph representations.

DIFFormer: Scalable (Graph) Transformers Induced by Energy Constrained Diffusion

Qitian Wu, Chenxiao Yang, Wentao Zhao, Yixuan He, David Wipf and Junchi Yan

International Conference on Learning Representations (ICLR) 2023 oral presentation, ranking among top 0.5%

Summary: We propose a geometric diffusion framework with energy constraints and show its solution aligns with widely used attention networks, upon which we propose diffusion-based Transformers.

Energy-based Out-of-Distribution Detection for Graph Neural Networks

Qitian Wu, Yiting Chen, Chenxiao Yang, and Junchi Yan

International Conference on Learning Representations (ICLR) 2023

Summary: We extract a OOD detection model from GNN classifier through energy-based models and energy-based belief propagation, reducing FPR95 over SOTAs by up to 44.8%.

Graph Neural Networks are Inherently Good Generalizers: Insights by Bridging GNNs and Multi-Layer Perceptrons

Chenxiao Yang, Qitian Wu, Jiahua Wang and Junchi Yan

International Conference on Learning Representations (ICLR) 2023

Summary: We identify that the efficacy of GNNs over MLP mostly stems from its inherent better generalization, demonstrated by experiments on sixteen benchmarks and neural tangent kernel theory.

NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classification

Qitian Wu, Wentao Zhao, Zenan Li, David Wipf and Junchi Yan

Advances in Neural Information Processing Systems (NeurIPS) 2022 spotlight presentation

Summary: We propose a scalable graph Transformer with efficient all-pair message passing achieved in O(N) complexity. The global attention over 2M nodes only requires 4GB memory.

Learning Substructure Invariance for Out-of-Distribution Molecular Representations

Nianzu Yang, Kaipeng Zeng, Qitian Wu, Xiaosong Jia and Junchi Yan

Advances in Neural Information Processing Systems (NeurIPS) 2022 spotlight presentation

Summary: We propose a invariant learning approach for molecular property prediction under distribution shifts and achieve SOTA results on OGB-mol and DrugOOD benchmarks.

Geometric Knowledge Distillation: Topology Compression for Graph Neural Networks

Chenxiao Yang, Qitian Wu and Junchi Yan

Advances in Neural Information Processing Systems (NeurIPS) 2022

Summary: We explore geometric knowledge distillation, empowered by neural heat kernel, that can generalize the topological knowledge from larger GNNs to smaller one.

Towards Out-of-Distribution Sequential Event Prediction: A Causal Treatment

Chenxiao Yang, Qitian Wu, Qingsong Wen, Zhiqiang Zhou, Liang Sun and Junchi Yan

Advances in Neural Information Processing Systems (NeurIPS) 2022

Summary: We use causal analysis to reveal the limitations of Maximum Likelihood Estimation for sequential prediction under distribution shifts and propose an effective treatment based on backdoor adjustment.

Handling Distribution Shifts on Graphs: An Invariance Perspective

Qitian Wu, Hengrui Zhang, Junchi Yan and David Wipf

International Conference on Learning Representations (ICLR) 2022

Summary: We formulate out-of-distribution generalization on graphs and discuss how to leverage (causal) invariance principle for handling graph-based distribution shifts.

Towards Open-World Recommendation: An Inductive Model-based Collaborative Filtering Approach

Qitian Wu, Hengrui Zhang, Xiaofeng Gao, Junchi Yan and Hongyuan Zha

International Conference on Machine Learning (ICML) 2021 spotlight presentation

Summary: We propose a latent structure inference model to handle new unseen users in the testing phase of recommender systems.

Towards Open-World Feature Extrapolation: An Inductive Graph Learning Approach

Qitian Wu, Chenxiao Yang and Junchi Yan

Advances in Neural Information Processing Systems (NeurIPS) 2021

Summary: We propose a graph representation learning approach for handling feature space expansion from training data to testing data.

From Canonical Correlation Analysis to Self-supervised Graph Neural Networks

Hengrui Zhang, Qitian Wu, Junchi Yan, David Wipf and Philip S. Yu

Advances in Neural Information Processing Systems (NeurIPS) 2021

Summary: We introduce a simple-yet-effective contrastive objective for self-supervised learning on graphs.

Bridging Explicit and Implicit Deep Generative Models via Neural Stein Estimators

Qitian Wu, Han Gao and Hongyuan Zha

Advances in Neural Information Processing Systems (NeurIPS) 2021

Summary: We leverage the Stein's distance as a novel tool to construct a theoretically grounded bridging term between two families of deep generative models.

Dual Graph Attention Networks for Deep Latent Representation of Multifaceted Social Effects in Recommender Systems

Qitian Wu, Hengrui Zhang, Xiaofeng Gao, Peng He, Paul Weng, Han Gao and Guihai Chen

The Web Conference (WWW) 2019 long oral representation

Summary: We propose a dual graph attention model that captures the social homophily and influence effects among users and items in recommender systems.

Learning Divergence Fields for Shift-Robust Message Passing

Qitian Wu, Fan Nie, Chenxiao Yang and Junchi Yan

International Conference on Machine Learning (ICML) 2024

How Graph Neural Networks Learn: Lessons from Training Dynamics

Chenxiao Yang, Qitian Wu, David Wipf, Ruoyu Sun and Junchi Yan

International Conference on Machine Learning (ICML) 2024

Graph Out-of-Distribution Detection Goes Neighborhood Shaping

Tianyi Bao, Qitian Wu, Zetian Jiang, Yiting Chen, Jiawei Sun and Junchi Yan

International Conference on Machine Learning (ICML) 2024

Graph Out-of-Distribution Generalization via Causal Intervention

Qitian Wu, Fan Nie, Chenxiao Yang, Tianyi Bao and Junchi Yan

The Web Conference (WWW) 2024 oral presentation

Rethinking Cross-Domain Sequential Recommendation Under Open-World Assumptions

Wujiang Xu, Qitian Wu, Runzhong Wang, Mingming Ha, Qiongxu Ma, Linxun Chen, Bing Han and Junchi Yan

The Web Conference (WWW) 2024

SGFormer: Simplifying and Empowering Transformers for Large-Graph Representations

Qitian Wu, Wentao Zhao, Chenxiao Yang, Hengrui Zhang, Fan Nie, Haitian Jiang, Yatao Bian and Junchi Yan

Advances in Neural Information Processing Systems (NeurIPS) 2023

Unleashing the Power of Graph Data Augmentation on Covariate Distribution Shift

Yongduo Sui, Qitian Wu, Jiancan Wu, Qing Cui, Longfei Li, Jun Zhou, Xiang Wang, Xiangnan He

Advances in Neural Information Processing Systems (NeurIPS) 2023

GraphGlow: Universal and Genralizable Structure Learning for Graph Neural Networks

Wentao Zhao, Qitian Wu, Chenxiao Yang and Junchi Yan

ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD) 2023

MoleRec: Combinatorial Drug Recommendation with SubstructureAware Molecular Representation Learning

Nianzu Yang, Kaipeng Zeng, Qitian Wu, Junchi Yan

The Web Conference (WWW) 2023

DIFFormer: Scalable (Graph) Transformers Induced by Energy Constrained Diffusion

Qitian Wu, Chenxiao Yang, Wentao Zhao, Yixuan He, David Wipf and Junchi Yan

International Conference on Learning Representations (ICLR) 2023 oral presentation, ranking among top 0.5%

Energy-based Out-of-Distribution Detection for Graph Neural Networks

Qitian Wu, Yiting Chen, Chenxiao Yang, and Junchi Yan

International Conference on Learning Representations (ICLR) 2023

Graph Neural Networks are Inherently Good Generalizers: Insights by Bridging GNNs and Multi-Layer Perceptrons

Chenxiao Yang, Qitian Wu, Jiahua Wang and Junchi Yan

International Conference on Learning Representations (ICLR) 2023

NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classification

Qitian Wu, Wentao Zhao, Zenan Li, David Wipf and Junchi Yan

Advances in Neural Information Processing Systems (NeurIPS) 2022 spotlight presentation

Learning Substructure Invariance for Out-of-Distribution Molecular Representations

Nianzu Yang, Kaipeng Zeng, Qitian Wu, Xiaosong Jia and Junchi Yan

Advances in Neural Information Processing Systems (NeurIPS) 2022 spotlight presentation

Geometric Knowledge Distillation: Topology Compression for Graph Neural Networks

Chenxiao Yang, Qitian Wu and Junchi Yan

Advances in Neural Information Processing Systems (NeurIPS) 2022

Towards Out-of-Distribution Sequential Event Prediction: A Causal Treatment

Chenxiao Yang, Qitian Wu, Qingsong Wen, Zhiqiang Zhou, Liang Sun and Junchi Yan

Advances in Neural Information Processing Systems (NeurIPS) 2022

GraphDE: A Generative Framework for Debiased Learning and Out-of-Distribution Detection on Graphs

Zenan Li, Qitian Wu, Fan Nie and Junchi Yan

Advances in Neural Information Processing Systems (NeurIPS) 2022

Variational Inference for Training Graph Neural Networks in Low-Data Regime through Joint Structure-Label Estimation

Danning Lao, Xinyu Yang, Qitian Wu, Junchi Yan

ACM SIGKDD Conference on Knowledge Discovery and Data Mining (SIGKDD) 2022

DICE: Domain-attack Invariant Causal Learning for Improved Data Privacy Protection and Adversarial Robustness

Qibing Ren, Yiting Chen, Yichuan Mo, Qitian Wu, Junchi Yan

ACM SIGKDD Conference on Knowledge Discovery and Data Mining (SIGKDD) 2022

Handling Distribution Shifts on Graphs: An Invariance Perspective

Qitian Wu, Hengrui Zhang, Junchi Yan and David Wipf

International Conference on Learning Representations (ICLR) 2022

Trading Hard Negatives and True Negatives: A Debiased Contrastive Collaborative Filtering Approach

Chenxiao Yang, Qitian Wu, Jipeng Jin, Junwei Pan, Xiaofeng Gao, and Guihai Chen

International Joint Conference on Artificial Intelligence (IJCAI) 2022

ScaleGCN: Efficient and Effective Graph Convolution via Channel-Wise Scale Transformation

Tianqi Zhang, Qitian Wu, Junchi Yan, Yunan Zhao and Bing Han

IEEE Transactions on Neural Networks and Learning Systems (TNNLS) 2022

Towards Open-World Recommendation: An Inductive Model-based Collaborative Filtering Approach

Qitian Wu, Hengrui Zhang, Xiaofeng Gao, Junchi Yan and Hongyuan Zha

International Conference on Machine Learning (ICML) 2021 spotlight presentation

Towards Open-World Feature Extrapolation: An Inductive Graph Learning Approach

Qitian Wu, Chenxiao Yang and Junchi Yan

Advances in Neural Information Processing Systems (NeurIPS) 2021

From Canonical Correlation Analysis to Self-supervised Graph Neural Networks

Hengrui Zhang, Qitian Wu, Junchi Yan, David Wipf and Philip S. Yu

Advances in Neural Information Processing Systems (NeurIPS) 2021

Bridging Explicit and Implicit Deep Generative Models via Neural Stein Estimators

Qitian Wu, Han Gao and Hongyuan Zha

Advances in Neural Information Processing Systems (NeurIPS) 2021

Seq2Bubbles: Region-Based Embedding Learning for User Behaviors in Sequential Recommenders

Qitian Wu, Chenxiao Yang, Shuodian Yu, Xiaofeng Gao and Guihai Chen

ACM International Conference on Information & Knowledge Management (CIKM) 2021 spotlight presentation

Learning High-Order Graph Convolutional Networks via Adaptive Layerwise Aggregation Combination

Tianqi Zhang, Qitian Wu and Junchi Yan

IEEE Transactions on Neural Networks and Learning Systems (TNNLS) 2021

Sentimem: Attentive memory networks for sentiment classification in user review

Xiaosong Jia, Qitian Wu, Xiaofeng Gao and Guihai Chen

International Conference on Database Systems for Advanced Applications (DASFAA) 2020

Learning Latent Process from High-Dimensional Event Sequences via Efficient Sampling

Qitian Wu, Zixuan Zhang, Xiaofeng Gao, Junchi Yan and Guihai Chen

Advances in Neural Information Processing Systems (NeurIPS) 2019

Feature Evolution Based Multi-Task Learning for Collaborative Filtering with Social Trust

Qitian Wu, Lei Jiang, Xiaofeng Gao, Xiaochun Yang and Guihai Chen

International Joint Conference on Artificial Intelligence (IJCAI) 2019

Dual Sequential Prediction Models Linking Sequential Recommendation and Information Dissemination

Qitian Wu, Yirui Gao, Xiaofeng Gao, Paul Weng and Guihai Chen

ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD) 2019

Dual Graph Attention Networks for Deep Latent Representation of Multifaceted Social Effects in Recommender Systems

Qitian Wu, Hengrui Zhang, Xiaofeng Gao, Peng He, Paul Weng, Han Gao and Guihai Chen

The Web Conference (WWW) 2019 long oral representation

EPAB: Early pattern aware bayesian model for social content popularity prediction

Qitian Wu, Chaoqi Yang, Xiaofeng Gao, Peng He and Guihai Chen

IEEE international conference on data mining (ICDM) 2018

Adversarial training model unifying feature driven and point process perspectives for event popularity prediction

Qitian Wu, Chaoqi Yang, Hengrui Zhang, Xiaofeng Gao, Paul Weng and Guihai Chen

ACM International Conference on Information & Knowledge Management (CIKM) 2018

EPOC: A survival perspective early pattern detection model for outbreak cascades

Chaoqi Yang, Qitian Wu, Xiaofeng Gao and Guihai Chen

International Conference on Database and Expert Systems Applications (DEXA) 2018

Honors & Awards

Scholar Star in SJTU (the highest academic award for PhD students in the university), 2023

National Scholarship (only 0.2% for Chinese PhD students), 2022, 2023

Baidu PhD Fellowship (only 10 recipients worldwide), 2021 [link]

Microsoft Research PhD Fellowship (only 11 recipients in Asia), 2021 [link]

Global Top 100 Rising Star in Artificial Intelligence, 2021 [link]

Yuanqing Yang Scholarship (only 3 master students in the department), 2019

Outstanding Graduate in Shanghai (only 5%), 2018

Outstanding Thesis of Undergraduates, 2018

Outstanding Winner, INFORMS Awards, Mathematical Contest in Modeling, Data Insights Problem (top 3 out of 4748 teams in the worldwide, the INFORMS Awards selects only one team), 2018 [link]

Lixin Tang Scholarship (only 60 students across all academic levels in the university), 2017, 2018

National Scholarship (only 1% for undergraduate students), 2016, 2017

The 1st-Class Academic Excellence Scholarship (top 1 in the department), 2016, 2017

National Second Award, China Undergraduate Mathematical Contest in Modeling, 2016

First Award, Physics Contest of Chinese College Students, 2015

Invited Talks

Learning with Non-IID Data from Physics Principles, Oct. 2023, ByteDance AI Lab [slides]

Towards Graph Transformers at Scale, July 2023, LOG Seminar [video] [slides]

Transformers induced by Energy-Constrained Diffusion, Mar. 2023, Amazon AI Lab

Learning on Graphs Under Open-world Assumptions, Mar. 2022, Bosch AI Center [slides]

Recent Advances in Graph Machine Learning, Nov. 2022, Huawei Noah's Ark Lab

Scalable Graph Transformers with Linear Complexity, Nov. 2022, AI Times [video]

Out-of-Distribution Generalization and Extrapolation on Graphs, Oct. 2022, Learning on Graphs Seminar [video] [slides]

Out-of-Distribution Generalization and Extrapolation on Graphs, May. 2022, Alipay, Alibaba

From Graph Learning to Open-World Representation Learning, Apr. 2022, AI Drive Paperweekly [video] [slides]

Service

Program Committee/Reviewer
ICML: 2021, 2022, 2023
NeurIPS: 2021, 2022, 2023
ICLR: 2022, 2023, 2024
SIGKDD: 2023
WWW: 2023
AAAI: 2021, 2022, 2023
IJCAI: 2021, 2022, 2023
CVPR: 2021, 2022, 2023
ICCV: 2021
TKDE
TNNLS

Acknowledgement

This website is built on the template by Martin Saveski