πββοΈ About Me
Hello! I am a third-year Ph.D. student in the School of Computing and Data Science (HKU-CDS) at the University of Hong Kong (HKU), advised by Prof. Reynold Cheng.
Research Interest: building resource-aware intelligent data systems that enable reliable querying and decision-making under different types of resource constraints: (1) limited data access, (2) imperfect data representations, and (3) expensive computation.
I actively collaborate with renowned researchers including Prof. Sihem Amer-Yahia (CNRS) and Prof. Laks V.S. Lakshmanan (UBC), and I am always open to discussing new research ideas and collaborations. Feel free to reach out via email.
I hold a first-class honors B.Sc. degree in Mathematics and Decision Analytics from HKU. My undergraduate thesis, supervised by Dr. Adela Lau, established my foundation in machine learning and representation learning. I further broadened my research experience through internships and research programs, including the 2022 RIPS Program at NUS Institute of Mathematical Sciences, where I collaborated with Grab on graph-based fraud detection.
π₯ News
- 2025.11: Β ππ Research paper accepted at SIGMOD 2026.
- 2025.06: GRF proposal funded (Graph Hypothesis Testing).
- 2024.06: Research paper accepted at VLDB 2024.
- 2024.03: Demo paper accepted at WWW 2024.
- 2023.05: Paper accepted at CITERS 2023 (AI for Education).
π Publications
My publications focus on reliable querying and decision-making, spanning from different types of resource constraints, including limited data access, imperfect data representations, and expensive computation.
On Efficient Approximate Aggregate Nearest Neighbor Queries over Learned Representations
Carrie Wang, Sihem Amer-Yahia, Laks V. S. Lakshmanan, Reynold Cheng
Increasingly, modern data systems rely on learned representations that are approximate, noisy, or heterogeneous in quality. This work studies how to answer aggregate queries accurately and efficiently when data representations are unreliable, by selectively combining cheap proxy models with expensive oracle computations.
A Sampling-based Framework for Hypothesis Testing on Large Attributed Graphs
Carrie Wang, Chrysanthi Kosyfaki, Sihem Amer-Yahia, Reynold Cheng
Large-scale graph analytics often require testing complex hypotheses over enormous numbers of structural instances, making exhaustive enumeration infeasible. This work develops a hypothesis-aware sampling framework that enables reliable statistical testing on large attributed graphs under strict data access budgets.
HINCare: An Intelligent Helper Recommender System for Elderly Care
Carrie Wang, Wentao Ning, Xiaoman Wu, Reynold Cheng
CITERS 2023Algorithms for Enabling and Verifying Upskilling, Sihem Amer-Yahia, Reynold Cheng, Nassim Bouarour, Carrie WangKnowledge-Based Systems 2023Using a novel clustered 3D-CNN model for improving crop future price prediction, Liege Cheung, Carrie Wang, Adela S M Lau, Rogers M C Chan
π» Research Experience
-
Research Intern, Huawei Hong Kong Research Center (HKRC), 2012 Laboratory
Jun 2025 β Oct 2025
Research on probabilistic user behavior modeling and spoof fingerprint detection. -
Participant, The 6th ACM Europe Summer School on Data Science
Jun 2025
Best Lightning Talk Award (Top 4/42).
π©βπ« Teaching Experience
-
Fall 2024Teaching Assistant, Introduction to Database Management Systems
-
Spring 2024Teaching Assistant, Big Data Management
-
Fall 2020Teaching Assistant, Probability and Statistics I
π Education
-
Ph.D. in Computer Science, School of Computing and Data Science, HKU
2023.09 β 2027.08 (expected) -
B.Sc. in Mathematics and Decision Analytics, School of Computing and Data Science, HKU
2018.09 β 2023.01
π Honors and Awards
-
2023β2027HKU Postgraduate Scholarship
-
2023First Class Honors
-
2020β2021Yu Kam Tim Chan Siu Hing Award in Artificial Intelligence and Data Science
-
2018β2022HKU Foundation Entrance Scholarship
-
2019β2022Deanβs Honors List
-
2017β2018First Prize, MOMENTUM Social Innovation Contest