VO Thanh Vinh

VO Thanh Vinh

Research Fellow, National University of Singapore

I am currently a Research Fellow at the School of Computing - National University of Singapore (NUS), working with Professors Leong Tze Yun and Arnab Bhattacharyya. My research interests include causal inference, causal discovery, reinforcement learning, and point processes.

I completed my PhD in computer science at the NUS on problems related to causal inference from observational data. I was advised by Professor Leong Tze Yun.

News

02 May 2024Our paper 'Reward Shaping for Reinforcement Learning with An Assistant Reward Agent' was just accepted to ICML 2024.
26 Apr 2024Our paper 'Decoupled Prompt-Adapter Tuning for Continual Activity Recognition' was just accepted to CoLLAs 2024.
21 Dec 2023Our paper 'Mixed-Initiative Bayesian Sub-Goal Optimization in Hierarchical Reinforcement Learning' was just accepted to AAMAS 2024 as a full paper publication.
07 Apr 2023Our paper 'Discovering Low-Dimensional Causal Pathways between Multiple Interacting Neuronal Populations' was just accepted to CogSci 2023 as full paper publication.
04 Jan 2023Our paper 'Hierarchical Reinforcement Learning with Human-AI Collaborative Sub-Goals Optimization' was just accepted to AAMAS 2023 as an extended abstract.
08 Oct 2022I received the NeurIPS 2022 Scholar Award.
15 Sep 2022Our paper 'An Adaptive Kernel Approach to Federated Learning of Heterogeneous Causal Effects' was accepted to NeurIPS 2022.
02 Aug 2022Our paper 'Adaptive Multi-Source Causal Inference from Observational Data' was accepted to CIKM 2022 full paper track.
29 Jul 2022I am awarded the Dean's Graduate Research Excellence Award AY2021/2022.
11 Jun 2022Our paper 'Transfer Kernel Learning for Multi-source Transfer Regression' was accepted to IEEE TPAMI.
16 May 2022Our paper 'Bayesian Federated Estimation of Causal Effects from Observational Data' was accepted to UAI 2022.

Selected publications

  1. Reward Shaping for Reinforcement Learning with An Assistant Reward Agent.
    Haozhe Ma, Kuankuan Sima, Thanh Vinh Vo, Di Fu, Tze-Yun Leong.
    41st International Conference on Machine Learning (ICML), 2024.
    [PDF] [OpenReview]
  2. Decoupled Prompt-Adapter Tuning for Continual Activity Recognition.
    Di Fu, Thanh Vinh Vo, Haozhe Ma, Tze-Yun Leong.
    Conference on Lifelong Learning Agents (CoLLAs), 2024.
    [PDF]
  3. Mixed-Initiative Bayesian Sub-Goal Optimization in Hierarchical Reinforcement Learning.
    Haozhe Ma, Thanh Vinh Vo, Tze-Yun Leong.
    23rd International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2024.
    (full paper)
    [PDF]
  4. Hierarchical Reinforcement Learning with Human-AI Collaborative Sub-Goals Optimization.
    Haozhe Ma, Thanh Vinh Vo, Tze-Yun Leong.
    22nd International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2023.
    (extended abstract)
    [PDF]
  5. An Adaptive Kernel Approach to Federated Learning of Heterogeneous Causal Effects.
    Thanh Vinh Vo, Arnab Bhattacharyya, Young Lee, Tze-Yun Leong.
    36th Conference on Neural Information Processing Systems (NeurIPS), 2022.
    [PDF] [OpenReview] [Supplementary] [Slides] [Poster] [Code]
  6. Bayesian Federated Estimation of Causal Effects from Observational Data.
    Thanh Vinh Vo, Young Lee, Trong Nghia Hoang, Tze-Yun Leong.
    38th Conference on Uncertainty in Artificial Intelligence (UAI), 2022.
    [PDF] [OpenReview] [Supplementary] [Code]
  7. Adaptive Multi-Source Causal Inference from Observational Data.
    Thanh Vinh Vo, Pengfei Wei, Trong Nghia Hoang, Tze-Yun Leong.
    31st ACM International Conference on Information and Knowledge Management (CIKM), 2022.
    (full paper track)
    [PDF] [Slides] [Code]
  8. Transfer Kernel Learning for Multi-source Transfer Regression.
    Pengfei Wei, Thanh Vinh Vo, Xinghua Qu, Yew Soon Ong, Zejun Ma.
    IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2022. (Impact Factor: 24.314)
    [PDF]
  9. Causal Modeling with Stochastic Confounders.
    Thanh Vinh Vo, Pengfei Wei, Wicher Bergsma, Tze-Yun Leong.
    24th International Conference on Artificial Intelligence and Statistics (AISTATS), 2021.
    [PDF] [Supplementary] [Code]
  10. Z-Transforms and its Inference on Partially Observable Point Processes.
    Young Lee, Thanh Vinh Vo, Kar Wai Lim, Harold Soh.
    27th International Joint Conference on Artificial Intelligence (IJCAI), 2018.
    [PDF]
  11. Generation Meets Recommendation: Proposing Novel Items for Groups of Users.
    Thanh Vinh Vo, Harold Soh.
    ACM Recommender Systems Conference (RecSys), 2018. (Best Long Paper Award Runner-up)
  12. Instance Reduction for Time Series Classification using MDL Principle.
    Thanh Vinh Vo, Duong Tuan Anh.
    Intelligent Data Analysis 21(3), IOS Press, 2017.

Preprints and work in progress

  1. Self-supervised Mask Graph Autoencoder via Neighbor Reconstruction for Graphs with Heterophily.
    Jiele Wu, Thanh Vinh Vo, Tze-Yun Leong.
  2. Highly Efficient Self-Adaptive Reward Shaping for Reinforcement Learning.
    Haozhe Ma, Zhengding Luo, Thanh Vinh Vo, Kuankuan Sima, Tze-Yun Leong.
  3. Federated Causal Inference from Observational Data.
    Thanh Vinh Vo, Young Lee, Tze-Yun Leong.
    [PDF]
  4. A Distribution Over DAGs for Uncertain Causal Discovery.
    Thanh Vinh Vo, Young Lee, Arnab Bhattacharyya, Tze-Yun Leong.

Services

  • Reviewer/PC member:
    • NeurIPS 2023
    • ICLR 2024, 2025
    • UAI 2023, 2024
    • AAAI 2023, 2024, 2025
    • AISTATS 2022, 2023, 2024, 2025
    • IJCAI 2024
    • AAMAS 2025
    • KDD 2024, 2025
  • Journal reviewer: Expert Systems with Applications, Computers & Industrial Engineering.