I am an Assistant Professor at the School of Computer Science, Carleton University. I obtained my Ph.D. at the University of Alberta, working with Prof. Dale Shuurmans and Prof. Russ Greiner at Amii. My research focuses on the fundamental understanding of machine learning algorithms and their applications in different fields.

Openings: I’m looking for self-motivated students to work on reinforcement learning, transfer learning, federated learning and machine learning in general. If you are interested, please send me your CV. Prospective MSc and PhD students applying to the School of Computer Science at Carleton University are encouraged to mention my name as the preferred supervisor.

  • Email: junfengwen A~T gmail D-O-T com (for general academic work)
  • Email: junfeng.wen A~T carleton D-O-T ca (for Carleton related work)


Education

2013 - 2020 Ph.D. in Statistical Machine Learning
Department of Computing Science, University of Alberta
2011 - 2013 M.Sc. in Computing Science
Department of Computing Science, University of Alberta
2007 - 2011 Bachelor of Engineering (with Honor)
College of Computer Science and Technology, CKC College, Zhejiang University

Publications & Preprints

  • Yangchen Pan*, Junfeng Wen*, Chenjun Xiao, and Philip Torr. An MRP Formulation for Supervised Learning: Generalized Temporal Difference Learning Models. [Arxiv]
  • Xiangyu (Johnny) Ma, Wei Shi and Junfeng Wen. An Enhanced Combinatorial Contextual Neural Bandit Approach for Client Selection in Federated Learning. In European Interdisciplinary Cybersecurity Conference, 2024.
  • Andre Telfer, Afsoon Alidadi Shamsabadi, George Savin, Junfeng Wen and Alfonso Abizaid. Inverse Reinforcement Learning to Study Motivation in Mouse Behavioral Paradigms. In CVPR CV4Animals Workshop, 2023.
  • Shivam Kalra*, Junfeng Wen*, Jesse C Cresswell*, Maksims Volkovs and Hamid R Tizhoosh. Decentralized Federated Learning through Proxy Model Sharing. In Nature Communications, 2023. [Arxiv] [code]
  • Amy Sui*, Junfeng Wen*, Yenson Lau, Brendan Leigh Ross and Jesse C. Cresswell. Find Your Friends: Personalized Federated Learning with the Right Collaborators. In FL-NeurIPS Workshop, 2022. [long version]
  • Ramki Gummadi, Saurabh Kumar, Junfeng Wen and Dale Schuurmans. A Parametric Class of Approximate Gradient Updates for Policy Optimization. In International Conference of Machine Learning (ICML), 2022. [pdf]
  • Junfeng Wen, Saurabh Kumar, Ramki Gummadi and Dale Schuurmans. Characterizing the Gap Between Actor-Critic and Policy Gradient. In International Conference of Machine Learning (ICML), 2021. [pdf]
  • Junfeng Wen*, Bo Dai*, Lihong Li and Dale Schuurmans. Batch Stationary Distribution Estimation. In International Conference of Machine Learning (ICML), 2020. [pdf]
  • Junfeng Wen, Russ Greiner and Dale Schuurmans. Domain Aggregation Networks for Multi-Source Domain Adaptation. In International Conference of Machine Learning (ICML), 2020. [pdf] [code]
  • Junfeng Wen, Yanshuai Cao and Ruitong Huang. Few-Shot Self Reminder to Overcome Catastrophic Forgetting. In NeurIPS Workshop on Continual Learning, 2018. [pdf] [long version]
  • Chen Ma, Junfeng Wen and Yoshua Bengio. Universal Successor Representations for Transfer Reinforcement Learning. In Sixth International Conference on Learning Representations (ICLR) Workshop, 2018. [pdf] [long version]
  • Vignesh Ganapathiraman, Xinhua Zhang, Yaoliang Yu and Junfeng Wen. Convex Two-Layer Modeling with Latent Structure. In Twenty-Ninth Neural Information Processing Systems (NeurIPS), 2016. [pdf]
  • Junfeng Wen, Negar Hassanpour and Russ Greiner. Weighted Gaussian Process for Estimating Treatment Effect. In NeurIPS Workshop on Inference and Learning of Hypothetical and Counterfactual Interventions in Complex Systems, 2016.
  • Junfeng Wen, Russ Greiner and Dale Schuurmans. Correcting Covariate Shift with the Frank-Wolfe Algorithm. In Twenty-Fourth International Joint Conference on Artificial Intelligence (IJCAI), 2015. [pdf] [code]
  • Martha White, Junfeng Wen, Michael Bowling and Dale Schuurmans. Optimal Estimation of Multivariate ARMA Models. In Twenty-Ninth Annual Conference on Artificial Intelligence (AAAI), 2015. Also invited to ICRA 2015. [pdf] [code]
  • Junfeng Wen, Chun-Nam Yu and Russ Greiner. Robust Learning under Uncertain Test Distributions: Relating Covariate Shift to Model Misspecification. In International Conference of Machine Learning (ICML), 2014. [pdf] [code]

Teaching Experience

  • COMP 4010/4900/5900 Introduction to Reinforcement Learning, Carleton University (2023 Winter/Fall, 2024 Winter/Fall)
  • COMP 3105 Introduction to Machine Learning, Carleton University (2022/2023/2024 Fall)
  • CMPUT 274 Introduction to Tangible Computing, University of Alberta (2015 Fall)

Professional Services

  • Conference reviewer: NeurIPS (Top 200), ICML, ICLR, AAAI, IJCAI, ACML
  • Journal reviewer: JMLR, MLJ (Member of Editorial Board), TPAMI