提出多尺度图对比学习新框架，减少信息损失并提升表示一致性。
Multiplex Graph Contrastive Learning with Soft Negatives
- 用多层表示作有效补丁，增强跨尺度一致性
- 基于位置亲和力设计软负例，降低错误负样本影响
- 在多个公开数据集上达到顶尖性能，适合图学习研究者
图对比学习（GCL）旨在从图结构数据中学习包含最大一致信息的节点或图表示。尽管当前以节点级对比为主，已有研究开始探索跨尺度的一致性，但往往导致信息丢失且受干扰特征污染。本文提出MUX-GCL，一种新型跨尺度对比学习范式，利用多层表示作为有效补丁。该方法通过基于位置亲和力的软负例对比策略，有效修正跨尺度中的错误负样本对，从而减少信息损失。大量下游实验表明，MUX-GCL在多个公开数据集上取得多项领先结果。理论分析进一步证明，该目标函数是原始输入特征与输出嵌入互信息的更严格下界，为该范式提供了理论支持。代码已开源于 https://github.com/MUX-GCL/Code。
原文摘要 · Abstract (English)
Graph Contrastive Learning (GCL) seeks to learn nodal or graph representations that contain maximal consistent information from graph-structured data. While node-level contrasting modes are dominating, some efforts commence to explore consistency across different scales. Yet, they tend to lose consistent information and be contaminated by disturbing features. Here, we introduce MUX-GCL, a novel cross-scale contrastive learning paradigm that utilizes multiplex representations as effective patches. While this learning mode minimizes contaminating noises, a commensurate contrasting strategy using positional affinities further avoids information loss by correcting false negative pairs across scales. Extensive downstream experiments demonstrate that MUX-GCL yields multiple state-of-the-art results on public datasets. Our theoretical analysis further guarantees the new objective function as a stricter lower bound of mutual information of raw input features and output embeddings, which rationalizes this paradigm. Code is available at https://github.com/MUX-GCL/Code.
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。