StructComp：在训练图对比学习中以结构压缩替代传播
StructComp: Substituting Propagation with Structural Compression in Training Graph Contrastive Learning
AI总结：
针对图对比学习的可扩展性瓶颈，本文提出StructComp框架，通过扩散矩阵的稀疏低秩近似压缩节点，免训练期消息传递并减少对比样本对，理论上可近似原损失且兼具正则化效果，实验证明其更省资源并提升性能。
摘要：
图对比学习（GCL）已成为学习图数据的强大工具，但其可扩展性仍是一项重大挑战。在本文中，我们提出了一个简单而有效的训练框架，称为结构压缩（StructComp），以解决这一问题。受扩散矩阵上的稀疏低秩近似启发，StructComp使用压缩后的节点训练编码器。这使编码器在训练阶段无需执行任何消息传递，并显著减少了对比损失中的样本对数量。我们从理论上证明，原始GCL损失可以由StructComp计算出的对比损失近似。此外，StructComp可被视为GCL模型的额外正则化项，从而产生更鲁棒的编码器。在多个数据集上的实证研究表明，与原始GCL模型和可扩展训练方法相比，StructComp大幅降低了时间和内存消耗，同时提升了模型性能。
英文摘要：
Graph contrastive learning (GCL) has become a powerful tool for learning graph data, but its scalability remains a significant challenge. In this work, we propose a simple yet effective training framework called Structural Compression (StructComp) to address this issue. Inspired by a sparse low-rank approximation on the diffusion matrix, StructComp trains the encoder with the compressed nodes. This allows the encoder not to perform any message passing during the training stage, and significantly reduces the number of sample pairs in the contrastive loss. We theoretically prove that the original GCL loss can be approximated with the contrastive loss computed by StructComp. Moreover, StructComp can be regarded as an additional regularization term for GCL models, resulting in a more robust encoder. Empirical studies on various datasets show that StructComp greatly reduces the time and memory consumption while improving model performance compared to the vanilla GCL models and scalable training methods.
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。
