图神经网络的谱贪心核心集
Spectral Greedy Coresets for Graph Neural Networks
AI总结：
本文提出谱贪心图核心集（SGGC），通过两阶段贪心选择自我图，加速大规模图上的GNN训练，无需预训练，适用于低同质性图，并在十个数据集上显著优于现有方法。
摘要：
大规模图在节点分类任务中的普遍存在严重阻碍了图神经网络（GNNs）的实际应用。节点采样、图粗化和数据集压缩是提高数据效率的有效策略。然而，由于图节点之间的相互依赖性，核心集选择（即选择数据示例子集的方法）尚未成功应用于加速大规模图上的GNN训练，需要特殊处理。本文研究用于GNN的图核心集，并通过基于谱嵌入选择自我图（即节点周围的邻域子图）来避免相互依赖问题。我们将GNN的核心集选择问题分解为两个阶段：广泛分布的自我图的粗略选择和对其拓扑结构进行多样化的精细选择。我们设计了一种贪心算法，近似优化这两个目标。我们的谱贪心图核心集（SGGC）可扩展到具有数百万个节点的图，无需模型预训练，并适用于低同质性图。在十个数据集上的大量实验表明，SGGC在性能上大幅优于其他核心集方法，在不同GNN架构上具有良好的泛化能力，并且比图压缩快得多。
英文摘要：
The ubiquity of large-scale graphs in node-classification tasks significantly hinders the real-world applications of Graph Neural Networks (GNNs). Node sampling, graph coarsening, and dataset condensation are effective strategies for enhancing data efficiency. However, owing to the interdependence of graph nodes, coreset selection, which selects subsets of the data examples, has not been successfully applied to speed up GNN training on large graphs, warranting special treatment. This paper studies graph coresets for GNNs and avoids the interdependence issue by selecting ego-graphs (i.e., neighborhood subgraphs around a node) based on their spectral embeddings. We decompose the coreset selection problem for GNNs into two phases: a coarse selection of widely spread ego graphs and a refined selection to diversify their topologies. We design a greedy algorithm that approximately optimizes both objectives. Our spectral greedy graph coreset (SGGC) scales to graphs with millions of nodes, obviates the need for model pre-training, and applies to low-homophily graphs. Extensive experiments on ten datasets demonstrate that SGGC outperforms other coreset methods by a wide margin, generalizes well across GNN architectures, and is much faster than graph condensation.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
