EDiS: Edge Disjoint Subgraph Sparsification Framework for Graph Neural Networks

Key points

• Sparse GNN training reduces computation, but deciding which edges to keep can be costly.1
• EDiS decomposes the graph once into cacheable edge-disjoint subgraphs, then recombines them into graphs with edge-budget constraints across epochs and retention ratios without re-extracting structure.1
• We provide a combinatorial analysis of the per-epoch sampler, the composition step that draws a training graph from the cached decomposition.1
• We show that, under the default covering-forest selector, the stored decomposition deterministically preserves high-score cut edges, and we derive a selector-agnostic conditional bound on high-score cut survival in composed training graphs.1

Sources (2)

• [1]EDiS: Edge Disjoint Subgraph Sparsification Framework for Graph Neural Networks
  Hugging Face Daily Papers · Oct 6, 12:00 AM

  We introduce EDiS (Edge-Disjoint Subgraph sparsification framework), which separates one-time structural extraction from per-epoch graph composition.

  Sparse GNN training reduces computation, but deciding which edges to keep can be costly.

• [2]EDiS: Edge Disjoint Subgraph Sparsification Framework for Graph Neural Networks
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 6, 08:09 PM · same content

Extractive summary: sentences quoted from the sources.