Yikun Ban

Associate Professor
School of Computer Science and Engineering
Beihang University

I am a tenure-track associate professor in the School of Computer Science and Engineering at Beihang University and a memeber of the State Key Laboratory of Software Development Environment. Previously, I was a postdoc and obtained my Ph.D. degree at Computer Science, University of Illinois at Urbana-Champaign, where I worded closely with Prof. Jingrui He, Prof. Hanghang Tong, and Prof. Arindam Banerjee. Prior to this, I obtained my Master's degree from EECS, Peking University and bachelor's degree from Wuhan University.
I am interested in principled algorithms in the space of multi-armed bandits/reinforcement learning and deep learning, to solve real-world exploitation-exploration problems. Current research topics:
  • Neural Contextual Bandits - Foundations and Applications.
  • Language Models with Exploration.
  • Reinforcement Learning with Human Feedback.

yikunb2[at]illinois.edu
Lab Webpage
Google Scholar

News
  • 2024.12   "PageRank Bandit" is accepted by NeurIPS 2024, in which we first use bandit perspective to solve link prediction.
  • 2024.12   "Robust Neural Contextual Bandit" is accepted by NeurIPS 2024, in which we remove the Positive Definite assumption for NTK Matrix.
  • 2024.05   One paper is accepted by KDD 2024.
  • 2023.12   I passed my PhD defense on 19 December 2023.
  • 2022.09   One paper was accepted by NeurIPS 2022.
  • 2022.01   One paper was accepted by ICLR 2022 Spotlight. EE-Net provides a novel neural-based exploration strategy, distinct from standard UCB and TS.

Publications(*Equal Contribution)

  1. Yunzhe Qi, Yikun Ban, Arindam Banerjee, Jingrui He
    Robust Neural Contextual Bandit against Adversarial Corruptions
    Thirty-eighth Conference on Neural Information Processing Systems ( NeurIPS'24 )
  2. Yikun Ban*, Jiaru Zou*, Zihao Li, Yunzhe Qi, Dongqi Fu, Jian Kang, Hanghang Tong, Jingrui He
    PageRank Bandits for Link Prediction
    Thirty-eighth Conference on Neural Information Processing Systems ( NeurIPS'24 )
  3. Yikun Ban*, Yunzhe Qi*, Tianxin Wei, Lihui Liu, Jingrui He
    Meta Clustering of Neural Bandits
    ACM SIGKDD Conference on Knowledge Discovery and Data Mining ( KDD'24 )
  4. Yikun Ban, Yuchen Yan, Arindam Banerjee, Jingrui He
    Neural Exploitation and Exploration of Contextual Bandits
    Journal of Machine Learning Research ( JMLR'24 )
    To Appear
  5. Yikun Ban, Yunzhe Qi, Jingrui He
    Neural Contextual Bandits for Personalized Recommendation
    The Web Conference, Tutorial ( WWW'24)
    [ ]   []
  6. Yikun Ban, Ishika Agarwal, Ziwei Wu, Yada Zhu, Kommy Weldemariam, Hanghang Tong, and Jingrui He
    Neural Active Learning Beyond Bandits
    International Conference on Learning Representations ( ICLR'24 )
  7. Rohan Deb, Yikun Ban, Shiliang Zuo, Jingrui He, Arindam Banerjee
    Contextual Bandits with Online Neural Regression
    International Conference on Learning Representations ( ICLR'24 )
  8. Yunzhe Qi*, Yikun Ban*, Tianxin Wei, Jiaru Zou, Huaxiu Yao, and Jingrui He
    Meta-Learning with Neural Bandit Scheduler
    Thirty-seventh Conference on Neural Information Processing Systems ( NeurIPS'23 )
  9. Yunzhe Qi*, Yikun Ban*, and Jingrui He
    Graph Neural Bandits
    ACM SIGKDD Conference on Knowledge Discovery and Data Mining ( KDD'23 )
  10. Yikun Ban*, Yuheng Zhang*, Hanghang Tong, Arindam Banerjee, and Jingrui He
    Improved Algorithms for Neural Active Learning
    Thirty-sixth Conference on Neural Information Processing Systems ( NeurIPS'22 )
  11. Dongqi Fu, Yikun Ban, Hanghang Tong, Ross Maciejewski, and Jingrui He
    DISCO: Comprehensive and Explainable Disinformation Detection
    ACM International Conference on Information and Knowledge Management (Demo Track) ( CIKM'22 )
  12. Yunzhe Qi, Yikun Ban, and Jingrui He
    Neural Bandit with Arm Group Graph
    ACM SIGKDD Conference on Knowledge Discovery and Data Mining ( KDD'22 )
  13. Yikun Ban, Yuchen Yan, Arindam Banerjee, and Jingrui He
    EE-Net: Exploitation-Exploration Neural Networks in Contextual Bandits
    International Conference on Learning Representations ( ICLR'22, Spotlight)
  14. Yikun Ban and Jingrui He
    Convolutional Neural Bandit for Visual-aware Recommendation
    Preprint: ArXiv:2107.07438
  15. Yikun Ban, Jingrui He, and Curtiss B. Cook
    Multi-Facet Contextual Bandits: A Neural Network Perspective
    ACM SIGKDD Conference on Knowledge Discovery and Data Mining ( KDD'21 )
  16. Yikun Ban and Jingrui He
    Local Clustering in Contextual Multi-Armed Bandits
    The Web Conference ( WWW'21 )
  17. Yuchen Yan, Lihui Liu, Yikun Ban, Baoyu Jing, and Hanghang Tong
    Dynamic Knowledge Graph Alignment
    AAAI Conference on Artificial Intelligence ( AAAI'21 )
  18. Yikun Ban and Jingrui He
    Generic Outlier Detection in Multi-Armed Bandit
    ACM SIGKDD Conference on Knowledge Discovery and Data Mining ( KDD'20 )
  19. Yikun Ban, Xin liu, Ling Huang, Yitao Duan, Xue Liu, and Wei Xu
    No Place to Hide: Catching Fraudulent Entities in Tensors
    The Web Conference ( WWW ’19 )

Education

    Sep. 2019 - Dec. 2023
    Ph.D., Computer Science, University of Illinois at Urbana-Champaign, Illinois, US
    Sep. 2016 - Jul. 2019
    M.S., Computer Science, Peking University, Beijing, China
    Sep. 2012 - Jul. 2016
    B.S., School of Software Engineering, Wuhan University, Wuhan, China

Selected Awards and Honors

  • 10/2022   NeurIPS 2022 Scholar Award
  • 05/2022   Outstanding ICML'22 Reviewer
  • 08/2020 & 08/2021   KDD’20, KDD’21, Student Travel Award
  • 09/2018   Outstanding Students of Peking University
  • 06/2016   Outstanding Graduate Students of Wuhan University
  • 8/2015   First Prized, The “China Software Cup” Software Design Competition for College Students (Top 0.1%, 2859 teams involved)
  • 11/2014   Second Prized in National Finals, First Prized in Provincial Finals, The “Challenge Cup” China College Student’s Entrepreneurship Competition (Top 0.2%, 5000+ teams involved)

Internship

  • May. 2022 - Aug. 2022, Applied Scientist Intern, AI Platform, Amazon

Services

  • Program Committee:ICML'22, KDD'22, AAAI'22, KDD'21, IJCAI'21, CIKM'21