5 papers
EDiS: Edge Disjoint Subgraph Sparsification Framework for Graph Neural Networks
Sai Karthik Navuluru, Siddhartha Shankar Das, Franck Dernoncourt +7
Sparse GNN training reduces computation, but deciding which edges to keep can be costly. Reusing one sparse graph is cheap, but locks training to a fixed topology, while varying it…
Scaffold: Support Graph Theory Based Sparsification for Graph Neural Networks
Siddhartha Shankar Das, Sai Karthik Navuluru, S M Ferdous +7
Graph neural networks (GNNs) rely on message passing over graph edges, making their computational and memory costs strongly dependent on graph density. Graph sparsification offers…
A Federated Learning Framework for Privacy-Preserving Oral Cancer Screening on Smartphones
Lena D. Swamikannan, Akshay Bhagwan Sonawane, Jay S. Patel +3
Data are the cornerstone of robust AI models. However, in the medical domain, access to reliable data is constrained by regulatory requirements and patient privacy, and clinical or…
Unifying Graph Neural Networks Through a Common Layer Equation
Sai Karthik Navuluru, Siddhartha Shankar Das, Bo Ni +9
Graph neural networks are commonly described through family-specific equations whose notation obscures shared computations and structural differences. We introduce a common layer e…
Robust Classification of Oral Cancer with Limited Training Data
Akshay Bhagwan Sonawane, Lena D. Swamikannan, Lakshman Tamil
Oral cancer ranks among the most prevalent cancers globally, with a particularly high mortality rate in regions lacking adequate healthcare access. Early diagnosis is crucial for r…