Scholar
Fan Yang
Google Scholar ID: RXFeW-8AAAAJ
Assistant Professor of Computer Science, Wake Forest University
Citations & Impact
Citations
5,594
H-index
27
i10-index
38
Publications
20
Co-authors
12
list available
Contact
No contact links provided.
Publications
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
- Recently received the CRII award (project title: 'Towards Efficient Interpretation for Explainable Learning: A Computational Perspective on Attribution and Recourse') and the R21 award (project title: 'Towards Interpretable Imaging-based Gastric Cancer Prognosis via Prototypical and Attentional Deep Learning'). Student Hugo was selected for Honorable Mention of the 2024-2025 Outstanding Undergraduate Researcher Award (URA) and as the recipient of the 2024-2025 John W. Sawyer Prize in Computer Science.
Research Experience
- Currently a Tenure-Track Assistant Professor in the Department of Computer Science at Wake Forest University. Previously worked or interned with J.P. Morgan AI Research, Visa Research, and Meta AI.
Education
- Ph.D. in Computer Science from Rice University, supervised by Dr. Xia (Ben) Hu
Background
- Research interests: Data Mining and Machine Learning, with a focus on Trustworthy AI (including Interpretable Learning and Model Explainability). The overall goal is to make AI auditable, comprehensible, ethical, fair, responsible, robust, safe, and verifiable. Additionally, interested in downstream applications of Trustworthy AI such as Misinformation Detection, Recommender Systems, Health Informatics, and Financial Forecasting, with intersections in Computer Vision (CV), Natural Language Processing (NLP), and Human-Computer Interaction (HCI).
Miscellany
- Actively recruiting self-motivated graduate and undergraduate students who have enthusiasm for generally defined Artificial Intelligence. Financial support is available for students who are intended to participate and contribute to publication-level research projects. Students with strong programming skills or solid mathematics/statistics backgrounds are highly preferred.
