Rocky Chen

Rocky Tong Chen is currently an Associate Professor and ARC DECRA Fellow with the Data Science Discipline, School of Electrical Engineering and Computer Science, The University of Queensland. Dr Chen's main research interests include recommender systems, LLM agents, graph and sequential data mining, and social media content moderation. His research outputs shares a common focus on developing accurate, efficient, and trustworthy data mining solutions to discover actionable patterns and intelligence from large-scale user data to facilitate prediction and recommendation in a wide range of domains. To date, Dr Chen has published 90+ peer-reviewed papers in the most prestigious, CORE A*/A-ranked and CCF A-ranked conferences (e.g., KDD, SIGIR, WWW, ICDM, ICDE, AAAI and IJCAI) and journals (e.g., VLDBJ, IEEE TKDE, IEEE TNNLS, ACM TOIS and WWWJ). Dr Chen's work has attracted 7,500+ citations and an h-index of 40 on Google Scholar. a Field-Weighted Citation Impact of 4.51 (SciVal), i.e., his publications attract 4.51 times of the citations in comparison to similar papers of the same age, type and area. According to CNCI (Web of Science), 10 and 36 of his papers are respectively the top-1% and top-10% most cited. His publications have won 4 Best Paper Awards, 1 Best Paper Nomination, and 2 Travel Awards. Dr Chen has been regularly providing services in the data science discipline as reviewers for CORE A*/A journals like TKDE, TNNLS, TOIS, and as program committee members for CORE A*/A conferences like KDD, SIGIR, NeurIPS, WSDM, ICDM, ACL. He is one of the Area Chairs of top conferences KDD, WWW, and ACL in 2024-2025, and the Program Chair of the 2024 Australasian Database Conference (ADC’24). In 2025, he is appointed as an Associate Editor of the SJR Q1-ranked journal Neural Networks. Besides, he led and delivered a series of technical tutorials at WWW (the No. 1 international web mining conference) in 2022, 2024, and 2025, as well as WSDM’25 (CORE A-ranked conference) and DASFAA’23 (top database conference), which all aimed to promote trustworthy, resource-efficient, and unbiased personalisation algorithms. Data Mining, Recommender Systems, Predictive Analytics, Machine Learning, Health Informatics

[2026] Decoding age-stratified mutational landscapes in CNS lymphoma via genomic and survival profiling for precision oncology [2026] LEFT: Learnable Fusion of Tri-view Tokens for Unsupervised Time Series Anomaly Detection [2026] Prompt-Unknown Promotion Attacks against LLM-based Sequential Recommender Systems [2026] ProMax: Exploring the Potential of LLM-derived Profiles with Distribution Shaping for Recommender Systems [2026] Single-cell analyses identify the ginseng embryonic protoderm as a native compartment for high-efficiency ginsenoside production [2026] DriftNavi: Talk through Your Data Drift with LLMs [2026] ProEx: a unified framework leveraging large language model with profile extrapolation for recommendation [2026] Efficient content-based recommendation model training via noise