LOW Kian Hsiang

Associate Professor
Director of AI Research, AI Singapore
Ph.D. (Electrical & Computer Engineering, Carnegie Mellon University, 2009)
B.Sc. (Computer Science, National University of Singapore, 2001)
M.Sc. (Computer Science, National University of Singapore, 2002)
COM2-02-58
651 64719

http://www.comp.nus.edu.sg/~lowkh/research.html

Research Areas

  • Artificial Intelligence

Research Sub Areas

  • Decision Making & Planning
  • Machine Learning
  • Multi-Agent Systems & Algorithmic Game Theory
  • Robotics
  • Trustworthy AI

Research Interests

  • Probabilistic Machine Learning (e.g., Bayesian deep learning, Gaussian process, Bayesian non-parametric models)
  • Data-Efficient Machine Learning (e.g., Bayesian optimization, meta-learning, active learning, and adaptive sampling)
  • Multi-Party Machine Learning (e.g., federated/distributed/collaborative learning, decentralized data fusion, privacy-preserving machine learning)
  • Reinforcement Learning and Multi-Agent Reinforcement Learning
  • Planning Under Uncertainty
  • Multi-Agent/Robot Systems
  • Computational Sustainability

Profile

Dr. Bryan Low is an Associate Professor of Computer Science at the National University of Singapore and the Director of AI Research at AI Singapore. He obtained the B.Sc. (Hons.) and M.Sc. degrees in Computer Science from National University of Singapore, Singapore, in 2001 and 2002, respectively, and the Ph.D. degree in Electrical and Computer Engineering from Carnegie Mellon University, Pittsburgh, Pennsylvania, in 2009. His research interests include probabilistic & automated machine learning, planning under uncertainty, and multi-agent/robot systems. Dr. Low is the recipient of the (1) Andrew P. Sage Best Transactions Paper Award for the best paper published in all 3 of the IEEE Transactions on Systems, Man, and Cybernetics - Parts A, B, and C in 2006; (2) National University of Singapore Overseas Graduate Scholarship for Ph.D. studies in Carnegie Mellon University (CMU) in 2004-2009; (3) Singapore Computer Society Prize for Best M.Sc. Thesis in School of Computing, National University of Singapore in 2003; and (4) Faculty Teaching Excellence Award in School of Computing, National University of Singapore in 2017-2018. Dr. Low has served as a World Economic Forum’s Global Future Councils Fellow for the Council on the Future of Artificial Intelligence and Robotics from Sep 2016 to Jun 2018 and an IEEE Robotics & Automation Society (RAS) Distinguished Lecturer for the IEEE RAS Technical Committee on Multi-Robot Systems in Mar 2019. He has served as an organizing chair for the IEEE RAS Summer School on Multi-Robot Systems in Jun 2016, the AI Summer Schools in Jul 2019 and Aug 2020, and the NeurIPS 2021 Workshop on New Frontiers in Federated Learning. Dr. Low has also served as associate editors, area chairs and program committee members, and reviewers for premier AI (specifically, multiagent systems, AI planning, robotics, machine learning) conferences: IJCAI, AAAI, ECAI, AAMAS, ICAPS, RSS, IROS, ICRA, CoRL, NeurIPS, ICML, AISTATS, ICLR and journals: TKDE, JMLR, JAIR, MLJ, TNNLS, T-ASE, IJRR, T-RO, AURO, JFR, TOSN, JAAMAS. He was the top 5% reviewer for ICML 2019, top 33% reviewer for ICML 2020, and an expert reviewer for ICML 2021.

Research Group

Multi-Agent Planning, Learning, and Coordination Group (MapleCG) https://www.comp.nus.edu.sg/~lowkh/research.html https://ids.nus.edu.sg/TrustedCollabML.html https://www.youtube.com/watch?v=IhizVZdUv6k https://www.youtube.com/watch?v=DvE19gy1U0c

Our group is multi-disciplinary: CS, math, stats, physics, eng, data science. We believe in theory & practice. Our research cover probabilistic ML (Bayesian deep learning, Gaussian process), learning with less data (autoML, Bayesian optimization, meta-learning, active learning), multi-party ML (federated/collaborative ML, privacy-preserving ML), reinforcement learning & multi-agent/robot systems.

Research Project

Federated/Collaborative Machine Learning and Data Valuation https://ids.nus.edu.sg/TrustedCollabML.html https://www.youtube.com/watch?v=IhizVZdUv6k https://www.comp.nus.edu.sg/~lowkh/research.html

Collaborators: NG See Kiong     HE Bingsheng     HE Bingsheng     NG See Kiong     HE Bingsheng     NG See Kiong     HE Bingsheng     NG See Kiong

Federated/Collaborative ML is an appealing paradigm to build improved, high-quality ML models by training on aggregated data from many parties. How then can these parties be incentivized to collaborate & share their data?

Learning with Less Data: Automated Machine Learning with Bayesian Optimization https://www.comp.nus.edu.sg/news/features/2018-bryan-low/ https://www.comp.nus.edu.sg/~lowkh/research.html https://www.youtube.com/watch?v=DvE19gy1U0c

How can the hyperparameters of a deep learning model be automatically optimized without human intervention? How did the win-rate of AlphaGo improve from 50% to 66.5%? How can the nutrients, lighting and water conditions be optimized to maximize the crop yield? Look no further: Bayesian optimization is what you need.

Teaching Innovation

Selected Publications

  • Rachael Hwee Ling Sim, Yehong Zhang, Bryan Kian Hsiang Low, and Patrick Jaillet (2021). Collaborative Bayesian Optimization with Fair Regret. In Proceedings of the 38th International Conference on Machine Learning (ICML-21), pages 9691-9701 [21.5% Acceptance Rate].
  • Quoc Phong Nguyen, Zhongxiang Dai, Bryan Kian Hsiang Low, and Patrick Jaillet (2021). Value-at-Risk Optimization with Gaussian Processes. In Proceedings of the 38th International Conference on Machine Learning (ICML-21), pages 8063-8072 [21.5% Acceptance Rate].
  • Chi Thanh Lam, Trong Nghia Hoang, Bryan Kian Hsiang Low, and Patrick Jaillet (2021). Model Fusion for Personalized Learning. In Proceedings of the 38th International Conference on Machine Learning (ICML-21), pages 5948-5958 [21.5% Acceptance Rate].
  • Quoc Phong Nguyen, Bryan Kian Hsiang Low, and Patrick Jaillet (2021). Learning to Learn with Gaussian Processes. In Proceedings of the 37th Conference on Uncertainty in Artificial Intelligence (UAI-21) [26.5% Acceptance Rate].
  • Quoc Phong Nguyen, Zhaoxuan Wu, Bryan Kian Hsiang Low, and Patrick Jaillet (2021). Trusted-Maximizers Entropy Search for Efficient Bayesian Optimization. In Proceedings of the 37th Conference on Uncertainty in Artificial Intelligence (UAI-21) [26.5% Acceptance Rate].
  • Quoc Phong Nguyen, Sebastian Tay, Bryan Kian Hsiang Low, and Patrick Jaillet (2021). Top-k Ranking Bayesian Optimization. In Proceedings of the 35th AAAI Conference on Artificial Intelligence (AAAI-21), pages 9135-9143 [21.4% Acceptance Rate].
  • Quoc Phong Nguyen, Bryan Kian Hsiang Low, and Patrick Jaillet (2021). An Information-Theoretic Framework for Unifying Active Learning Problems. In Proceedings of the 35th AAAI Conference on Artificial Intelligence (AAAI-21), pages 9126-9134 [21.4% Acceptance Rate].
  • Trong Nghia Hoang, Shenda Hong, Cao Xiao, Bryan Kian Hsiang Low, and Jimeng Sun (2021). AID: Active Distillation Machine to Leverage Pre-Trained Black-Box Models in Private Data Settings. In Proceedings of the 30th The Web Conference (WWW'21), pages 3569-3581 [20.6% acceptance rate].
  • Quoc Phong Nguyen, Bryan Kian Hsiang Low, and Patrick Jaillet (2020). Variational Bayesian Unlearning. In Advances in Neural Information Processing Systems 33: 34th Annual Conference on Neural Information Processing Systems (NeurIPS'20), pages 16025-16036 [20.1% Acceptance Rate].
  • Zhongxiang Dai, Bryan Kian Hsiang Low, and Patrick Jaillet (2020). Federated Bayesian Optimization via Thompson Sampling. In Advances in Neural Information Processing Systems 33: 34th Annual Conference on Neural Information Processing Systems (NeurIPS'20), pages 9687-9699 [20.1% Acceptance Rate].
  • Sreejith Balakrishnan, Quoc Phong Nguyen, Bryan Kian Hsiang Low, and Harold Soh (2020). Efficient Exploration of Reward Functions in Inverse Reinforcement Learning via Bayesian Optimization.InAdvances in Neural Information Processing Systems 33: 34th Annual Conference on Neural Information Processing Systems (NeurIPS'20), pages 4187-4198 [20.1% Acceptance Rate].
  • Rachael Hwee Ling Sim, Yehong Zhang, Mun Choon Chan, and Bryan Kian Hsiang Low (2020). Collaborative Machine Learning with Incentive-Aware Model Rewards. In Proceedings of the 37th International Conference on Machine Learning (ICML-20), pages 8927-8936 [21.8% Acceptance Rate].
  • Zhongxiang Dai, Yizhou Chen, Bryan Kian Hsiang Low, Patrick Jaillet, and Teck-Hua Ho (2020). R2-B2: Recursive Reasoning-Based Bayesian Optimization for No-Regret Learning in Games. In Proceedings of the 37th International Conference on Machine Learning (ICML-20), pages 2291-2301 [21.8% Acceptance Rate].
  • Trong Nghia Hoang, Chi Thanh Lam, Bryan Kian Hsiang Low, and Patrick Jaillet (2020). Learning Task-Agnostic Embedding of Multiple Black-Box Experts for Multi-Task Model Fusion. In Proceedings of the 37th International Conference on Machine Learning (ICML-20), pages 4282-4292 [21.8% Acceptance Rate].
  • Dmitrii Kharkovskii, Zhongxiang Dai, and Bryan Kian Hsiang Low (2020). Private Outsourced Bayesian Optimization. In Proceedings of the 37th International Conference on Machine Learning (ICML-20), pages 5231-5242 [21.8% Acceptance Rate].
  • Dmitrii Kharkovskii, Chun Kai Ling, and Bryan Kian Hsiang Low (2020). Nonmyopic Gaussian Process Optimization with Macro-Actions. In Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics (AISTATS-20), pages 4593-4604 [28.6% acceptance rate].
  • Tong Teng, Jie Chen, Yehong Zhang, and Bryan Kian Hsiang Low (2020). Scalable Variational Bayesian Kernel Selection for Sparse Gaussian Process Regression. In Proceedings of the 34th AAAI Conference on Artificial Intelligence (AAAI-20), pages 5997-6004 [20.6% Acceptance Rate].
  • Haibin Yu, Yizhou Chen, Zhongxiang Dai, Bryan Kian Hsiang Low, and Patrick Jaillet (2019). Implicit Posterior Variational Inference for Deep Gaussian Processes. In Advances in Neural Information Processing Systems 32: 33rd Annual Conference on Neural Information Processing Systems (NeurIPS'19), pages 14475-14486 [3% Acceptance Rate Spotlight Presentation].
  • Yehong Zhang, Zhongxiang Dai, and Bryan Kian Hsiang Low (2019). Bayesian Optimization with Binary Auxiliary Information. In Proceedings of the 35th Conference on Uncertainty in Artificial Intelligence (UAI-19), pages 1222-1232 [26.2% Acceptance Rate Plenary Talk].
  • Zhongxiang Dai, Haibin Yu, Bryan Kian Hsiang Low, and Patrick Jaillet (2019). Bayesian Optimization Meets Bayesian Optimal Stopping. In Proceedings of the 36th International Conference on Machine Learning (ICML-19), pages 1496-1506 [22.6% Acceptance Rate].
  • Quang Minh Hoang, Trong Nghia Hoang, Bryan Kian Hsiang Low, and Carleton Kingsford (2019). Collective Model Fusion for Multiple Black-Box Experts. In Proceedings of the 36th International Conference on Machine Learning (ICML-19), pages 2742-2750 [22.6% Acceptance Rate].
  • Trong Nghia Hoang, Quang Minh Hoang, Bryan Kian Hsiang Low, and Jonathan P. How (2019). Collective Online Learning of Gaussian Processes in Massive Multi-Agent Systems. In Proceedings of the 33rd AAAI Conference on Artificial Intelligence (AAAI-19), pages 7850-7857 [16.2% Acceptance Rate].
  • Trong Nghia Hoang, Quang Minh Hoang, Ruofei Ouyang, and Bryan Kian Hsiang Low (2018). Decentralized High-Dimensional Bayesian Optimization with Factor Graphs. In Proceedings of the 32nd AAAI Conference on Artificial Intelligence (AAAI-18), pages 3231-3238 [24.55% Acceptance Rate].
  • Ruofei Ouyang and Bryan Kian Hsiang Low (2018). Gaussian Process Decentralized Data Fusion Meets Transfer Learning in Large-Scale Distributed Cooperative Perception. In Proceedings of the 32nd AAAI Conference on Artificial Intelligence (AAAI-18), pages 3876-3883 [24.55% Acceptance Rate].
  • Erik Daxberger and Bryan Kian Hsiang Low (2017). Distributed Batch Gaussian Process Optimization. In Proceedings of the 34th International Conference on Machine Learning (ICML-17), pages 951-960 [25.5% Acceptance Rate].
  • Quang Minh Hoang, Trong Nghia Hoang, and Bryan Kian Hsiang Low (2017). A Generalized Stochastic Variational Bayesian Hyperparameter Learning Framework for Sparse Spectrum Gaussian Process Regression. In Proceedings of the 31st AAAI Conference on Artificial Intelligence (AAAI-17), pages 2007-2014 [24.6% Acceptance Rate].
  • Trong Nghia Hoang, Quang Minh Hoang, and Bryan Kian Hsiang Low (2016). A Distributed Variational Inference Framework for Unifying Parallel Sparse Gaussian Process Regression Models. In Proceedings of the 33rd International Conference on Machine Learning (ICML-16), pages 382-391 [24.3% Acceptance Rate].
  • Chun Kai Ling, Bryan Kian Hsiang Low, and Patrick Jaillet (2016). Gaussian Process Planning with Lipschitz Continuous Reward Functions: Towards Unifying Bayesian Optimization, Active Learning, and Beyond. In Proceedings of the 30th AAAI Conference on Artificial Intelligence (AAAI-16), pages 1860-1866 [25.75% Acceptance Rate].
  • Yehong Zhang, Trong Nghia Hoang, Bryan Kian Hsiang Low, and Mohan Kankanhalli (2016). Near-Optimal Active Learning of Multi-Output Gaussian Processes. In Proceedings of the 30th AAAI Conference on Artificial Intelligence (AAAI-16), pages 2351-2357 [25.75% Acceptance Rate].
  • Jie Chen, Bryan Kian Hsiang Low, Patrick Jaillet, and Yujian Yao (2015). Gaussian Process Decentralized Data Fusion and Active Sensing for Spatiotemporal Traffic Modeling and Prediction in Mobility-on-Demand Systems. In IEEE Transactions on Automation Science and Engineering Special Issue on Networked Cooperative Autonomous Systems, volume 12, issue 3, pages 901-921.
  • Trong Nghia Hoang, Quang Minh Hoang, and Bryan Kian Hsiang Low (2015). A Unifying Framework of Anytime Sparse Gaussian Process Regression Models with Stochastic Variational Inference for Big Data. In Proceedings of the 32nd International Conference on Machine Learning (ICML-15), pages 569-578 [26.0% Acceptance Rate].
  • Quoc Phong Nguyen, Bryan Kian Hsiang Low, and Patrick Jaillet (2015). Inverse Reinforcement Learning with Locally Consistent Reward Functions. In C. Cortes, N. D. Lawrence, D. D. Lee, M. Sugiyama, R. Garnett, editors, Advances in Neural Information Processing Systems 28: 29th Annual Conference on Neural Information Processing Systems NeurIPS'15, pages 1747-1755 [21.9% Acceptance Rate].
  • Bryan Kian Hsiang Low, Jiangbo Yu, Jie Chen, and Patrick Jaillet (2015). Parallel Gaussian Process Regression for Big Data: Low-Rank Representation Meets Markov Approximation. In Proceedings of the 29th AAAI Conference on Artificial Intelligence (AAAI-15), pages 2821-2827 [26.67% Acceptance Rate].
  • Trong Nghia Hoang, Bryan Kian Hsiang Low, Patrick Jaillet, and Mohan Kankanhalli (2014). Nonmyopic ε-Bayes-Optimal Active Learning of Gaussian Processes. In Proceedings of the 31st International Conference on Machine Learning (ICML-14), pages 739-747 [25.0% Acceptance Rate].
  • Nuo Xu, Bryan Kian Hsiang Low, Jie Chen, Keng Kiat Lim, and Etkin B. Ozgul (2014). GP-Localize: Persistent Mobile Robot Localization using Online Sparse Gaussian Process Observation Model. In Proceedings of the 28th AAAI Conference on Artificial Intelligence (AAAI-14), pages 2585-2592 [28.3% Acceptance Rate].
  • Ruofei Ouyang, Bryan Kian Hsiang Low, Jie Chen, and Patrick Jaillet (2014). Multi-Robot Active Sensing of Non-Stationary Gaussian Process-Based Environmental Phenomena. In Proceedings of the 13th International Conference on Autonomous Agents and Multiagent Systems (AAMAS-14), pages 573-580 [23.8% Acceptance Rate].
  • Jie Chen, Bryan Kian Hsiang Low, and Colin Keng-Yan Tan (2013). Gaussian Process-Based Decentralized Data Fusion and Active Sensing for Mobility-on-Demand System. In Proceedings of the Robotics: Science and Systems Conference (RSS-13) [30.1% Acceptance Rate].
  • Trong Nghia Hoang and Bryan Kian Hsiang Low (2013). Interactive POMDP Lite: Towards Practical Planning to Predict and Exploit Intentions for Interacting with Self-Interested Agents. In Proceedings of the 23rd International Joint Conference on Artificial Intelligence (IJCAI-13), pages 2298-2305 [13.2% Acceptance Rate Oral Presentation].
  • Trong Nghia Hoang and Bryan Kian Hsiang Low (2013). A General Framework for Interacting Bayes-Optimally with Self-Interested Agents using Arbitrary Parametric Model and Model Prior. In Proceedings of the 23rd International Joint Conference on Artificial Intelligence (IJCAI-13), pages 1394-1400 [28.0% Acceptance Rate].
  • Nannan Cao, Bryan Kian Hsiang Low, and John M. Dolan (2013). Multi-Robot Informative Path Planning for Active Sensing of Environmental Phenomena: A Tale of Two Algorithms. In Proceedings of the 12th International Conference on Autonomous Agents and Multiagent Systems (AAMAS-13), pages 7-14 [22.9% Acceptance Rate].
  • Jie Chen, Nannan Cao, Bryan Kian Hsiang Low, Ruofei Ouyang, Colin Keng-Yan Tan, and Patrick Jaillet (2013). Parallel Gaussian Process Regression with Low-Rank Covariance Matrix Approximations. In Proceedings of the 29th Conference on Uncertainty in Artificial Intelligence (UAI-13), pages 152-161 [31.3% Acceptance Rate].
  • Jie Chen, Bryan Kian Hsiang Low, Colin Keng-Yan Tan, Ali Oran, Patrick Jaillet, John M. Dolan, and Gaurav S. Sukhatme (2012). Decentralized Data Fusion and Active Sensing with Mobile Sensors for Modeling and Predicting Spatiotemporal Traffic Phenomena. In Proceedings of the 28th Conference on Uncertainty in Artificial Intelligence (UAI-12), pages 163-173 [31.6% Acceptance Rate].
  • Prabhu Natarajan, Trong Nghia Hoang, Bryan Kian Hsiang Low, and Mohan Kankanhalli (2012). Decision-Theoretic Approach to Maximizing Observation of Multiple Targets in Multi-Camera Surveillance. In Proceedings of the 11th International Conference on Autonomous Agents and Multiagent Systems (AAMAS-12), pages 155-162 [20.4% Acceptance Rate].
  • Bryan Kian Hsiang Low, Jie Chen, John M. Dolan, Steve Chien, and David R. Thompson (2012). Decentralized Active Robotic Exploration and Mapping for Probabilistic Field Classification in Environmental Sensing. In Proceedings of the 11th International Conference on Autonomous Agents and Multiagent Systems (AAMAS-12), pages 105-112 [20.4% Acceptance Rate].
  • Bryan Kian Hsiang Low, John M. Dolan, and Pradeep K. Khosla (2011). Active Markov Information-Theoretic Path Planning for Robotic Environmental Sensing. In Proceedings of the 10th International Conference on Autonomous Agents and Multiagent Systems (AAMAS-11), pages 753-760 [22.1% Acceptance Rate].
  • Bryan Kian Hsiang Low, John M. Dolan, and Pradeep K. Khosla (2009). Information-Theoretic Approach to Efficient Adaptive Path Planning for Mobile Robotic Environmental Sensing. In Proceedings of the 19th International Conference on Automated Planning and Scheduling (ICAPS-09), pages 233-240 [33.9% Acceptance Rate].
  • Bryan Kian Hsiang Low, John M. Dolan, and Pradeep K. Khosla (2008). Adaptive Multi-Robot Wide-Area Exploration And Mapping. In Proceedings of the 7th International Conference on Autonomous Agents and Multiagent Systems (AAMAS-08), pages 23-30 [22.2% Acceptance Rate].
  • Bryan Kian Hsiang Low, Wee Kheng Leow, and Marcelo H. Ang, Jr. (2006). Autonomic Mobile Sensor Network with Self-Coordinated Task Allocation and Execution. In IEEE Transactions on Systems, Man, and Cybernetics - Part C: Applications and Reviews Special Issue on Engineering Autonomic Systems, volume 36, issue 3, pages 315-327 [ Andrew P. Sage Best Transactions Paper Award for the best paper published in all 3 of the IEEE Transactions on Systems, Man, and Cybernetics - Parts A, B, and C in 2006 ].
  • Bryan Kian Hsiang Low, Wee Kheng Leow, and Marcelo H. Ang, Jr. (2005). An Ensemble of Cooperative Extended Kohonen Maps for Complex Robot Motion Tasks. In Neural Computation, volume 17, issue 6, pages 1411-1445.
  • Bryan Kian Hsiang Low, Wee Kheng Leow, and Marcelo H. Ang, Jr. (2004). Task Allocation via Self-Organizing Swarm Coalitions in Distributed Mobile Sensor Network. In Proceedings of the 19th National Conference on Artificial Intelligence (AAAI-04), pages 28-33 [26.7% Acceptance Rate].
  • Bryan Kian Hsiang Low, Wee Kheng Leow, and Marcelo H. Ang, Jr. (2003). Action Selection for Single- and Multi-Robot Tasks Using Cooperative Extended Kohonen Maps. In Proceedings of the 18th International Joint Conference on Artificial Intelligence (IJCAI-03), pages 1505-1506 [27.6% Acceptance Rate].
  • Bryan Kian Hsiang Low, Wee Kheng Leow, and Marcelo H. Ang, Jr. (2002). A Hybrid Mobile Robot Architecture with Integrated Planning and Control. In Proceedings of the 1st International Joint Conference on Autonomous Agents and Multiagent Systems (AAMAS-02), pages 219-226 [26% Acceptance Rate].

Awards & Honours

  • IEEE Robotics & Automation Society (RAS) Distinguished Lecturer for the IEEE RAS Technical Committee on Multi-Robot Systems, Mar 2019
  • Invited to serve as a World Economic Forum’s Global Future Councils Fellow for the Council on the Future of Artificial Intelligence and Robotics, Sep 2016 – Jun 2018
  • Faculty Teaching Excellence Award in School of Computing, National University of Singapore, Aug 2017 - Jul 2018
  • Best PhD Forum Paper Award in 6th ACM/IEEE International Conference on Distributed Smart Cameras (ICDSC’12) won by my PhD student, Prabhu Natarajan, Nov 2012
  • Featured in Association for Unmanned Vehicle Systems International (AUVSI) Unmanned Systems Magazine "Ones to Watch" June 2010 issue
  • Andrew P. Sage Best Transactions Paper Award for the best paper (first author) published in all 3 of the IEEE Transactions on Systems, Man, and Cybernetics - Parts A, B, and C in 2006
  • NUS Overseas Graduate Scholarship for Ph.D. studies in Carnegie Mellon University, 2004-2009
  • Winner of Singapore Computer Society Prize for Best M.Sc. Thesis (among 81 graduates of M.Sc. by research) in SOC, NUS, 2002-2003

Teaching (2021/2022)

  • CS3244: Machine Learning