Scaffold：基于支撑图理论的图神经网络稀疏化方法

中文摘要 AI 辅助

图神经网络（GNNs）依赖沿图边的消息传递，因此其计算和内存成本与图密度密切相关。图稀疏化提供了一种自然的方式来降低这些成本，但不加区分地移除边可能会扭曲重要的通信结构并降低预测性能。我们提出了Scaffold，一种基于拓扑的、无监督的图稀疏化框架，其源自支撑图理论预条件子。Scaffold显式控制两个互补的结构量：扩张（dilation），衡量因移除边而产生的重路由路径的长度；以及拥塞（congestion），衡量这些重路由路径在保留支撑上的集中程度。通过联合控制扩张和拥塞，Scaffold在保留短通信路径的同时避免结构瓶颈。据我们所知，Scaffold是首个使用联合支撑路径扩张-拥塞准则的可扩展GNN稀疏化框架。在涵盖小图到大图的19个同质性和异质性基准上，Scaffold在评估的稀疏化及相关方法中取得了最佳综合排名。仅使用每个稀疏支撑原始边的10%-50%，Scaffold即可恢复或接近全图GNN的性能，同时使用不到全图训练一半的内存，并减少端到端训练时间（包括稀疏化开销）。我们在该https URL提供了开源软件包。

英文摘要

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 predictive performance. We introduce Scaffold, a topology-based, unsupervised graph sparsification framework derived from support graph theory preconditioners. Scaffold explicitly controls two complementary structural quantities: dilation, which measures the length of rerouting paths induced by removed edges, and congestion, which measures how strongly these rerouted paths concentrate on the retained support. By jointly controlling dilation and congestion, Scaffold preserves short communication paths while avoiding structural bottlenecks. To our knowledge, Scaffold is the first scalable GNN sparsification framework to use a joint supporting-path dilation-congestion criterion. Across 19 homophilic and heterophilic benchmarks spanning small to large graphs, Scaffold achieves the best aggregate rank among the evaluated sparsification and related methods. Using only 10%-50% of the original edges per sparse support, Scaffold recovers or closely approaches full-graph GNN performance while using less than half the memory of full-graph training and reducing end-to-end training time, including sparsification overhead. We provide an open-source software package at https://github.com/siddhartha047/Scaffold.

发表机构

• Pacific Northwest National Laboratory（太平洋西北国家实验室）
• University of Texas at Dallas（德克萨斯大学达拉斯分校）
• University of North Carolina at Charlotte（北卡罗来纳大学夏洛特分校）
• Adobe（Adobe公司）
• Boise State University（博伊西州立大学）
• Purdue University（普渡大学）

机构由 AI 辅助整理，请以论文原文为准。