通过多层次拓扑结构生成对比视图，提升图对比学习的表示能力。
HTG-GCL: Leveraging Hierarchical Topological Granularity from Cellular Complexes for Graph Contrastive Learning
- 构建多尺度环基细胞复形，实现拓扑粒度的层次化表达。
- 在多个基准上表现优于现有方法，显著提升图表示质量。
- 适合需要精细拓扑感知的下游任务，如节点分类与图聚类。
图对比学习（GCL）旨在通过对比同一图的不同视图来学习具有判别性的语义不变性，这些视图共享关键拓扑模式。然而，现有的基于结构增强的GCL方法往往难以识别任务相关的拓扑结构，更无法适应不同下游任务所需的粗粒度到细粒度拓扑粒度变化。为此，我们提出层级拓扑粒度图对比学习（HTG-GCL），该框架通过变换同一图生成多尺度环基细胞复形，体现拓扑粒度概念，从而生成多样化的拓扑视图。考虑到特定粒度可能包含误导性语义，我们提出多粒度解耦对比，并基于不确定性估计引入粒度特定加权机制。在多种基准上的综合实验表明，HTG-GCL有效提升了通过层次拓扑信息捕获有意义图表示的能力。
原文摘要 · Abstract (English)
Graph contrastive learning (GCL) aims to learn discriminative semantic invariance by contrasting different views of the same graph that share critical topological patterns. However, existing GCL approaches with structural augmentations often struggle to identify task-relevant topological structures, let alone adapt to the varying coarse-to-fine topological granularities required across different downstream tasks. To remedy this issue, we introduce Hierarchical Topological Granularity Graph Contrastive Learning (HTG-GCL), a novel framework that leverages transformations of the same graph to generate multi-scale ring-based cellular complexes, embodying the concept of topological granularity, thereby generating diverse topological views. Recognizing that a certain granularity may contain misleading semantics, we propose a multi-granularity decoupled contrast and apply a granularity-specific weighting mechanism based on uncertainty estimation. Comprehensive experiments on various benchmarks demonstrate the effectiveness of HTG-GCL, highlighting its superior performance in capturing meaningful graph representations through hierarchical topological information.
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。