Scholar
Shenyang Huang
Google Scholar ID: ljIXv6kAAAAJ
University of Oxford, McGill University, Montreal Institute for Learning Algorithms (Mila)
Citations & Impact
Citations
672
H-index
11
i10-index
12
Publications
20
Co-authors
51
list available
Publications
Resume (English only)
Academic Achievements
- Paper 'TGM: a Modular and Efficient Library for Machine Learning on Temporal Graphs' accepted at ICML 2025 CodeML Workshop; Delivering a tutorial on Relational Deep Learning and organizing the Temporal Graph Learning Workshop at KDD 2025; Paper 'T-GRAB: A Synthetic Diagnostic Benchmark for Learning on Temporal Graphs' selected for oral presentation at ML for Graph in the Era of GenAI workshop at KDD 2025.
Research Experience
- Postdoctoral Researcher at the Department of Computer Science, University of Oxford, working with Prof. Michael Bronstein; Previously, conducted research at McGill University and Mila - Quebec Artificial Intelligence Institute.
Education
- Ph.D. from School of Computer Science, McGill University, supervised by Prof. Reihaneh Rabbany and Prof. Guillaume Rabusseau; Honours in Computer Science from McGill University (2019).
Background
- Research interests include temporal graph neural networks, graph transformers, graph neural networks, and spectral methods. Focuses on designing machine learning models for complex and evolving real-world networks, referred to as Temporal Graph Learning (TGL). Actively engages in building the TGL community by organizing the TGL reading group and two editions of the TGL workshop @ NeurIPS 2022/2023.
Miscellany
- GitHub: https://github.com/shenyangHuang, LinkedIn: https://www.linkedin.com/in/shenyang-huang, X: shenyangHuang, Bluesky: shenyanghuangtg.bsky.social
