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 across epochs can require repeated sampling or recomputation. We introduce EDiS (Edge-Disjoint Subgraph sparsification framework), which se...
S. Navuluru, Siddhartha Shankar Das, Franck Dernoncourt et al.· 0 citations
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 natural way to reduce these costs, but removing edges indiscriminately can distort important communication structure and degrade predictiv...
Siddhartha Shankar Das, S. Navuluru, S. M. Ferdous et al.· 0 citations
SGS-GNN improves F1-scores by 4% relative to full training and up to 30% on heterophilic graphs and outperforms state-of-the-art methods by 4–7% at similar sparsity levels while reducing peak memory usage by up to 3.9×.
Siddhartha Shankar Das, Naheed Anjum Arafat, Muftiqur Rahman et al.· Proceedings of the 32nd ACM...· 1 citation
A common layer equation is introduced that represents covered architectures through seven components: an update domain, channel set, propagation bank, per-channel message maps, channel-fusion operator, ego/residual map, and update map, which exposes the empirical inverse problem of mapping measurable graph and task pro...
S. Navuluru, Siddhartha Shankar Das, B. Ni et al.· 0 citations
SGS-GNN improves F1-scores by 4% relative to full training and up to 30% on heterophilic graphs and outperforms state-of-the-art methods by 4–7% at similar sparsity levels while reducing peak memory usage by up to 3.9×.
Siddhartha Shankar Das, Naheed Anjum Arafat, Muftiqur Rahman et al.· Proceedings of the 32nd ACM...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
