提出可扩展的图嵌入方法，支持多任务学习且性能优于现有方案。
Scalable Deep Metric Learning on Attributed Graphs
- 基于多类三元组损失，拓展深度度量学习到带属性图
- 实现小批量训练与大规模图的高效表示构建
- 在节点分类等三项任务中表现更一致，适合大图多任务场景
针对大规模带属性图的嵌入表示构建及其下游多任务学习问题，本文提出一种可扩展的图嵌入方法。该方法将深度度量学习与无偏对比学习扩展至带属性图，支持小批量训练，并实现高可扩展性。基于多类三元组损失函数，提出两种算法：用于半监督学习的DMT和用于无监督学习的DMAT。理论分析给出下游节点分类任务的泛化界，首次建立三元组损失与对比学习之间的联系。大量实验表明，该方法在表示构建上具有高可扩展性，在节点聚类、节点分类和链接预测三个下游任务中均表现出比单一现有方法更优且更一致的性能。
原文摘要 · Abstract (English)
We consider the problem of constructing embeddings of large attributed graphs and supporting multiple downstream learning tasks. We develop a graph embedding method, which is based on extending deep metric and unbiased contrastive learning techniques to 1) work with attributed graphs, 2) enabling a mini-batch based approach, and 3) achieving scalability. Based on a multi-class tuplet loss function, we present two algorithms -- DMT for semi-supervised learning and DMAT-i for the unsupervised case. Analyzing our methods, we provide a generalization bound for the downstream node classification task and for the first time relate tuplet loss to contrastive learning. Through extensive experiments, we show high scalability of representation construction, and in applying the method for three downstream tasks (node clustering, node classification, and link prediction) better consistency over any single existing method.
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。