Rocky Tong Chen

Dr. Rocky Tong Chen is a Senior Lecturer and ARC DECRA Fellow at the Data Science Discipline within the School of Electrical Engineering and Computer Science at The University of Queensland. He maintains active affiliations with the Centre for Enterprise AI and the ARC Centre of Excellence for Children and Families Over the Lifecourse. His research focuses on developing accurate, efficient, and trustworthy data mining solutions to extract actionable patterns from large-scale user data.

Chen's research interests span Data Mining, Recommender Systems, Predictive Analytics, Machine Learning, and Health Informatics. His work demonstrates a strong emphasis on practical applications, particularly in developing lightweight and efficient algorithms for recommendation systems that can operate on resource-constrained devices. His research trajectory shows a clear progression from traditional recommender systems toward more privacy-preserving, decentralized, and trustworthy approaches that address real-world deployment challenges.

Chen has published over 70 peer-reviewed papers in top-tier venues including KDD, SIGIR, WWW, ICDM, ICDE, AAAI, and IJCAI, as well as leading journals like VLDBJ, IEEE TKDE, IEEE TNNLS, ACM TOIS, and WWWJ. His publication trends reveal a strong focus on federated learning, graph neural networks, and on-device recommendation systems in recent years.

• 3 Best Paper Awards
• 1 Best Paper Nomination
• 2 Travel Awards

Dr. Chen has secured multiple ARC grants including the Discovery Early Career Researcher Award (2023-2026) for 'Scalable and Lightweight On-Device Recommender Systems,' and is actively supervising numerous PhD students across various projects related to recommendation systems, data analytics, and machine learning. His supervision portfolio includes both principal and associate advisory roles, demonstrating his collaborative approach to research mentorship. His laboratory work focuses on developing practical implementations of recommender systems with an emphasis on efficiency, privacy, and real-world applicability.