发表机构
University of Texas at Dallas; Pacific Northwest National Laboratory; Adobe Research; University of North Carolina at Charlotte; Cisco; Purdue University（德克萨斯大学达拉斯分校; 太平洋西北国家实验室; Adobe研究院; 北卡罗来纳大学夏洛特分校; 思科; 普渡大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
EDiS框架将图结构一次性分解为可缓存的边不相交子图，并在各训练周期按边预算重组，兼顾稀疏训练效率与拓扑多样性，在19个基准上超越17个基线。
AI 中文摘要
稀疏图神经网络训练能减少计算量，但决定保留哪些边可能代价高昂。复用单个稀疏图虽然廉价，却将训练锁定在固定拓扑上，而跨周期改变拓扑则可能需要重复采样或重新计算。我们提出EDiS（边不相交子图稀疏化框架），它将一次性的结构提取与逐周期的图组合分离。EDiS将图一次性分解为可缓存的边不相交子图，然后在满足边预算约束和保留比例的情况下，跨周期将这些子图重新组合成图，而无需重新提取结构。我们的默认构造使用基于特征的分数和连续的最大分数覆盖森林，而相同的组合机制也支持其他边选择规则。我们对逐周期采样器（即从缓存分解中抽取训练图的组合步骤）进行了组合分析。我们证明，在默认的覆盖森林选择器下，存储的分解确定性地保留高分数割边，并且我们推导出一个与选择器无关的条件界，用于组合训练图中高分数割边的存活。在19个同质性、异质性和大规模节点分类基准上，与17个基线在相同边预算下进行比较，EDiS取得了最高的平均基准分数（准确率/ROC-AUC），并在排名方法中取得了最低的平均排名和与最优的差距。消融实验表明，在紧边预算下，结构分解和周期变化带来了最明显的收益。
英文摘要
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 separates one-time structural extraction from per-epoch graph composition. 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. Our default construction uses feature-based scores and successive maximum score covering forests, while the same composition mechanism also supports alternative edge selection rules. We provide a combinatorial analysis of the per-epoch sampler, the composition step that draws a training graph from the cached decomposition. 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. Across 19 homophilic, heterophilic, and large-scale node classification benchmarks against 17 baselines under the same edge budget, EDiS achieves the highest mean benchmark score (accuracy/ROC-AUC) and the lowest average rank and gap-to-best among ranked methods. Ablations show the clearest benefits of structural decomposition and epoch variation at tight edge budgets.
Comments46 pages, including references and appendices
