通过高斯空间对比学习，提升图表示自监督建模效果
Subgraph Gaussian Embedding Contrast for Self-Supervised Graph Representation Learning
- 将子图映射到结构化高斯空间，控制生成分布
- 用Wasserstein和Gromov-Wasserstein度量子图相似性
- 在多个数据集上超越或媲美现有方法
图表示学习（GRL）旨在将高维图结构数据编码为低维向量。自监督学习（SSL）因无需昂贵的人工标注而被广泛应用于GRL。本文提出一种新型子图高斯嵌入对比方法（SubGEC）。该方法引入子图高斯嵌入模块，自适应地将子图映射至结构化高斯空间，在保留输入子图特征的同时生成受控分布的子图。随后，采用最优传输距离（即Wasserstein与Gromov-Wasserstein距离）有效衡量子图间相似性，增强对比学习的鲁棒性。在多个基准测试上的大量实验表明， extit{SubGEC}性能优于或媲美当前最优方法。研究结果为自监督图表示学习方法的设计提供了新视角，强调了对比样本分布的重要性。
原文摘要 · Abstract (English)
Graph Representation Learning (GRL) is a fundamental task in machine learning, aiming to encode high-dimensional graph-structured data into low-dimensional vectors. Self-Supervised Learning (SSL) methods are widely used in GRL because they can avoid expensive human annotation. In this work, we propose a novel Subgraph Gaussian Embedding Contrast (SubGEC) method. Our approach introduces a subgraph Gaussian embedding module, which adaptively maps subgraphs to a structured Gaussian space, ensuring the preservation of input subgraph characteristics while generating subgraphs with a controlled distribution. We then employ optimal transport distances, more precisely the Wasserstein and Gromov-Wasserstein distances, to effectively measure the similarity between subgraphs, enhancing the robustness of the contrastive learning process. Extensive experiments across multiple benchmarks demonstrate that \method~outperforms or presents competitive performance against state-of-the-art approaches. Our findings provide insights into the design of SSL methods for GRL, emphasizing the importance of the distribution of the generated contrastive pairs.
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。