通过谱图对齐提升图对比学习性能，增强模型泛化能力。
Graph Contrastive Learning via Spectral Graph Alignment
- 设计新损失函数SpecMatch-CL，对齐不同视图的图嵌入结构。
- 在8个TU基准上达到新最优，低标签率下表现优异。
- 适用于无监督、半监督及迁移学习，尤其适合小样本场景。
现有对比学习方法（如InfoNCE）在优化图嵌入对齐时，缺乏对视图特异性图嵌入图（graph-of-graphs）全局结构的控制。本文提出SpecMatch-CL，通过最小化各视图生成的图嵌入图之间的归一化拉普拉斯矩阵差异，实现谱级对齐。理论上，在特定假设下，归一化拉普拉斯差可提供理想完美对齐损失与当前损失之间差异的上界，同时覆盖均匀损失。实验表明，SpecMatch-CL在八个TU基准上均取得新的最优结果，无论在无监督或低标签率半监督设置下均有显著提升；在PPI-306K和ZINC 2M数据集的迁移学习任务中也持续获得增益。
原文摘要 · Abstract (English)
Given augmented views of each input graph, contrastive learning methods (e.g., InfoNCE) optimize pairwise alignment of graph embeddings across views while providing no mechanism to control the global structure of the view specific graph-of-graphs built from these embeddings. We introduce SpecMatch-CL, a novel loss function that aligns the view specific graph-of-graphs by minimizing the difference between their normalized Laplacians. Theoretically, we show that under certain assumptions, the difference between normalized Laplacians provides an upper bound not only for the difference between the ideal Perfect Alignment contrastive loss and the current loss, but also for the Uniformly loss. Empirically, SpecMatch-CL establishes new state of the art on eight TU benchmarks under unsupervised learning and semi-supervised learning at low label rates, and yields consistent gains in transfer learning on PPI-306K and ZINC 2M datasets.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。