4 papers
Towards Metric-Faithful Neural Graph Matching
Jyotirmaya Shivottam, Subhankar Mishra
Graph Edit Distance (GED) is a fundamental, albeit NP-hard, metric for structural graph similarity. Recent neural graph matching architectures approximate GED by first encoding gra…
Graph Reconstruction from Differentially Private GNN Explanations
Rishi Raj Sahoo, Jyotirmaya Shivottam, Subhankar Mishra
Regulatory frameworks such as GDPR increasingly require that ML predictions be accompanied by post-hoc explanations, even when raw data and trained models cannot be released. Diffe…
QGShap: Quantum Acceleration for Faithful GNN Explanations
Haribandhu Jena, Jyotirmaya Shivottam, Subhankar Mishra
Graph Neural Networks (GNNs) have become indispensable in critical domains such as drug discovery, social network analysis, and recommendation systems, yet their black-box nature h…
QGraphLIME - Explaining Quantum Graph Neural Networks
Haribandhu Jena, Jyotirmaya Shivottam, Subhankar Mishra
Quantum graph neural networks offer a powerful paradigm for learning on graph-structured data, yet their explainability is complicated by measurement-induced stochasticity and the…