About Me
I am a fourth-year Computer Science Ph.D. candidate at the University of Amsterdam (INDElab), advised by Prof. Dr. Paul Groth and Dr. Klim Zaporojets, expecting to graduate in 2027.
I am on the job market, open to industry roles (Data Scientist / Machine Learning Engineer) and postdoctoral positions. Feel free to reach out at p.zhang@uva.nl or download my CV (PDF).
- Multi-modal knowledge graphs
- Entity linking
- Link prediction
- Recommendation
- Large language models
My research asks how machine learning models stay accurate as data drifts: the same person, product, or event looks different next year. I build models that fuse graph structure, text, images, and time for entity linking and recommendation. They improve over prior state of the art by up to 20% on entity linking and up to 10% on recommendation, with the largest gains on ambiguous, look-alike entities, where improvements reach 3x. All code, datasets, and benchmarks are public.
What’s next: extending temporal robustness to evolving knowledge bases and multi-modal foundation models, and applying it to real-world systems such as search and recommendation.
Education & Awards & Service
Education
- 2022 - Present: Ph.D. in Computer Science, INDElab, Faculty of Science, University of Amsterdam (UvA), the Netherlands. Supervisors: Prof. Dr. Paul Groth, Dr. Klim Zaporojets.
- 2019 - 2022: M.Eng. in Control Engineering, Faculty of Information Technology, Beijing University of Technology (BJUT), China. Supervisor: Prof. Dr. Yong Zhang.
Awards
- 2026: Conference travel grant for ACL 2026.
- 2022: Outstanding Master’s Thesis, Beijing University of Technology.
Service
- Reviewer / sub-reviewer: CIKM, ECAI, ESWC, PKDD.
- 2020 - 2021: Teaching assistant, Data Engineering (BJUT).