When optimizing computing architecture for specific computationally intensive tasks, such as evaluating or training a neural network, it is important to identify what computational subtasks will offer the greatest decrease in cost (e.g., wall clock time or energy usage). This problem is known as Hardware-Software (HS)...
Cameron Ibrahim, S. M. Ferdous, Erdal Mutlu et al.· 0 citations
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
Identifying influential nodes in complex networks is a critical challenge across domains ranging from social media analytics to epidemiology and marketing. Traditional influence maximization algorithms often fall short because they rely primarily on the network structure, overlooking the intrinsic qualities of individu...
Priyanka Gautam, Sai Munikoti, M. Halappanavar et al.· IEEE Access· 0 citations
To the authors' knowledge, Scaffold is the first scalable GNN sparsification framework to use a joint supporting-path dilation-congestion criterion, and across 19 homophilic and heterophilic benchmarks, Scaffold achieves the best aggregate rank among the evaluated sparsification and related methods.
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.
