GNN + GAT: Knowledge Representation Research
RESEARCH · IEEE BEST PAPER
Lead researcher and model developer
Final year project → GC4T 2025
IEEE · GC4T 2025
Existing GNN architectures struggle with multi-relational data and explainability in healthcare knowledge graphs — a gap between graph representation research and clinical application.
- Designed MetaGAT model architecture, ran benchmarks across Cora, PubMed, DBLP datasets, wrote and submitted the paper, presented at conference.
86.4% accuracy, 85.1% F1-score. Best Paper Award. Applied framework to disease prediction and recommender systems. Published under IEEE.
Prioritised benchmarkable accuracy on standard datasets over clinical validation (which would require IRB-level access). Explainability layer is v2 research.
“The MetaGAT architecture addressed a problem the community has been circling for a while — multi-relational graph learning with interpretability built into the design rather than added after. The benchmark results held up across all three datasets.”
The Outcome
Awarded Best Paper at GC4T 2025 by IEEE Pune Section. The MetaGAT framework demonstrated substantial leaps in predicting relationships across complex multi-relational graphical data, laying foundational architecture for subsequent healthcare recommender models and disease prediction pipelines.