提出基于链接表示的自监督模型，提升无属性图的链接预测性能。
Instance Discrimination for Link Prediction
- 用社区结构设计新数据增强方式，强化链接表征学习。
- 提出的L-GRACE和L-BGRL在无属性图上超越现有方法，媲美最优监督模型。
- 验证了图数据增强对链接预测的关键作用，适合图神经网络研究者。
近年来，实例判别模型已成为自监督学习的重要方案。尽管其在图像领域已取得显著成效，近年在图领域也证明对节点分类有效，但对链接预测任务的研究仍较少。本文首次系统评估了现有自监督模型在链接预测中的表现，发现性能主要取决于数据增强策略（类比计算机视觉）。为此，我们提出一种基于社区结构的新结构增强方法。核心贡献是构建两个新模型：L-GRACE与L-BGRL，它们直接基于链接表示而非节点表示进行学习，在无属性图上的性能显著优于现有方法，并在自监督与监督两种场景下达到当前最优水平。
原文摘要 · Abstract (English)
Recently, instance discrimination models have emerged as a major solution for self-supervised learning. Having already demonstrated its effectiveness in the image domain, instance discrimination learning is now proving equally convincing in the graph domain, in particular for node classification. However, fewer contributions have tackled the link prediction task. In this contribution, we propose to adapt existing methods to this context. We first provide a rigorous evaluation of existing self-supervised models in the field of link prediction, showing that the main performance depends on the augmentation process (like in computer vision). We then propose a new structural augmentation based on the community structure that is relevant for link prediction. Our main contribution introduces two new models, L-GRACE and L-BGRL, based on link representations instead of node representations, which improve the performance of the existing methods, especially on unattributed graphs, and we show that they perform on par with the state of the art, both in supervised and self-supervised contexts.
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。