collaborators

5 papers

cs.LG2026

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…

cs.LG2026

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…

cs.LG2026

GRAFT: Auditing Graph Neural Networks via Global Feature Attribution

Rishi Raj Sahoo, Subhankar Mishra

Graph Neural Networks (GNNs) achieve strong performance on node classification tasks but remain difficult to interpret, particularly with respect to which input features drive thei…

cs.LG2025

ReconXF: Graph Reconstruction Attack via Public Feature Explanations on Privatized Node Features and Labels

Rishi Raj Sahoo, Rucha Bhalchandra Joshi, Subhankar Mishra

Graph Neural Networks (GNNs) achieve high performance across many applications but function as black-box models, limiting their use in critical domains like healthcare and criminal…

cs.LG2025

Graph Neural Networks at a Fraction

Rucha Bhalchandra Joshi, Sagar Prakash Barad, Nidhi Tiwari +1

Graph Neural Networks (GNNs) have emerged as powerful tools for learning representations of graph-structured data. In addition to real-valued GNNs, quaternion GNNs also perform wel…