How Expressive are Knowledge Graph Foundation Models?
X Huang, P Barceló, MM Bronstein, İİ Ceylan, M Galkin, JL Reutter, MR Orth, How Expressive are Knowledge Graph Foundation Models?, arXiv preprint arXiv:2502.13339, 2025
CV
You can also download my CV here!
Education
- DPhil in Computer Science, University of Oxford, 2023-2026 (expected)
- MMathCompsci in Mathematics and Computer Science, University of Oxford, 2019-2023
Work experience
- Summer 2022: Mathematical Institute, University of Oxford, Summer Research Intern
- Explored the use of the Neural Control Differential Equation model to address the problem of protein folding
- Enhanced the capability of the Alphafold with rough path theory
- Developed a deep-learning based signature-inverse model to reduce the complexity of standard signature inversion
- Supervisors: Professor Terry Lyons and Dr. Cristopher Salvi
- Summer 2021: Alibaba Group, Machine Learning Engineer Intern
- Developed an object detection system for video subtitle-detection with Faster-RCNN model
- Conducted semantic analysis on OCR-detected titles to assess the quality of video descriptions
- Supervisor: Improved accuracy of object detection and classification by 10\% and were incorporated into production
- Summer 2020: Alirus Biotech., Machine Learning Engineer Intern
- Implemented image segmentation for Petri dish centering and Hough Transform for colony ROI detection
- Developed a colony counting algorithm by combining CNNs with traditional computer vision techniques
- Delivered a model for automatic colony counting with 20\% decreased in terms of regression metric
Skills
- Python
- PyTorch
- Tensorflow
- Triton (Huge Recommendation! For a faster python code!)
- MATLAB
- Haskell
- Scala
- LaTeX
Publications
One Model, Any Conjunctive Query: Graph Neural Networks for Answering Complex Queries over Knowledge Graphs
K Olejniczak, X Huang, İİ Ceylan, M Galkin, One Model, Any Conjunctive Query: Graph Neural Networks for Answering Complex Queries over Knowledge Graphs, arXiv preprint arXiv:2409.13959, 2024
Cooperative graph neural networks
B Finkelshtein, X Huang, M Bronstein, İİ Ceylan, Cooperative graph neural networks, arXiv preprint arXiv:2310.01267, 2023
A Novel Multiobjective Genetic Programming Approach to High-Dimensional Data Classification
Y. Zhou, N. Yang, X. Huang, J. Lee and S. Kwong, "A Novel Multiobjective Genetic Programming Approach to High-Dimensional Data Classification," in IEEE Transactions on Cybernetics, doi: 10.1109/TCYB.2024.3372070.
Theoretical Insights into Line Graph Transformation on Graph Learning
F Yang, X Huang, Theoretical Insights into Line Graph Transformation on Graph Learning, arXiv preprint arXiv:2410.16138, 2024
Link Prediction with Relational Hypergraphs
X Huang, MR Orth, P Barceló, MM Bronstein, İİ Ceylan, Link Prediction with Relational Hypergraphs, arXiv preprint arXiv:2402.04062, 2024
A Theory of Link Prediction via Relational Weisfeiler-Leman on Knowledge Graphs
Xingyue Huang, Miguel Romero Orth, İsmail İlkan Ceylan, and Pablo Barceló. A theory of link prediction via relational weisfeiler-leman on knowledge graphs. In NeurIPS, 2023.
Feature selection of high dimensional data by adaptive potential particle swarm optimization
X. Huang, Y. Chi and Y. Zhou, "Feature Selection of High Dimensional Data by Adaptive Potential Particle Swarm Optimization," 2019 IEEE Congress on Evolutionary Computation (CEC), Wellington, New Zealand, 2019, pp. 1052-1059, doi: 10.1109/CEC.2019.8790366.
An empirical study on two-child policy in china based on statistical analysis and machine learning
Yizhou Chi and Xingyue Huang and Yu Zhou, An Empirical Study on Two-child Policy in China Based on Statistical Analysis and Machine Learning, Proceedings of the 2nd International Conference on Social Science, Public Health and Education (SSPHE 2018)