4 papers · 1 filter
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…
Parametrized Exact Hardware-Software Partitioning
Cameron Ibrahim, S M Ferdous, Erdal Mutlu +2
When optimizing computing architecture for specific computationally intensive tasks, such as evaluating or training a neural network, it is important to identify what computational…
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…
DynLP: Parallel Dynamic Batch Update for Label Propagation in Semi-Supervised Learning
S M Shovan, Arindam Khanda, S M Ferdous +2
Semi-supervised learning aims to infer class labels using only a small fraction of labeled data. In graph-based semi-supervised learning, this is typically achieved through label p…