Lakshman Tamil

Train sparse GNNs with dynamic graph topologies across epochs without re-extracting structure, achieving state-of-the-art performance even at extreme edge budgets.

Achieving an impressive AUC of 0.929, this federated learning framework revolutionizes oral cancer screening by enabling secure, decentralized collaboration without compromising patient privacy.

A unified layer equation for GNNs reveals how over 200 architectures can be systematically compared and optimized for performance.