5 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…
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…
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…
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…