基于软负例的多重图对比学习
Multiplex Graph Contrastive Learning with Soft Negatives
AI总结：
针对现有跨尺度图对比学习易丢失一致信息、受干扰特征污染的问题，提出采用多重表示作为补丁、结合位置亲和度修正假负例的MUX-GCL范式，取得多项SOTA结果并获理论支撑。
摘要：
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。尽管节点级对比模式占据主流，已有部分工作开始探索跨尺度的一致性，但这类方法往往会丢失一致信息，且易受干扰特征污染。本文提出MUX-GCL，一种新型跨尺度对比学习范式，采用多重表示作为有效补丁。该学习模式在最小化污染噪声的同时，结合位置亲和度的匹配对比策略，通过修正跨尺度假负例对进一步避免信息损失。大量下游实验表明，MUX-GCL在公开数据集上取得多项最优（SOTA）结果。理论分析进一步证明，新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，为该范式提供了合理性支撑。代码可在https://github.com/MUX-GCL/Code获取。
英文摘要：
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.
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。
