通过时间跨度对比学习动态图表示，提升节点分类与异常检测效果。
Learning Dynamic Graph Representations through Timespan View Contrasts
- 引入时间平移不变性假设，利用不同时间段的对比学习建模节点演化。
- 在真实数据上，节点分类和异常检测准确率均优于现有方法。
- 无需复杂序列模型，计算效率高，适合金融、安全等实时场景。
现实世界中的图数据包含丰富的时序信息，但现有无监督图表示学习方法多依赖静态图的节点特征与拓扑结构，忽视了边的时间戳等动态成分。为此，本文提出一种新归纳偏置——时间平移不变性，即同一节点在不同时段应保持相似标签。基于此，构建动态图表示框架CLDG，通过跨时间段的对比学习使节点保持局部时间一致性。进一步提出CLDG++，引入图扩散以挖掘全局上下文关联，并设计局部-局部、局部-全局、全局-全局三重对比目标，增强表征能力。有趣的是，通过测量不同时段的一致性可自然生成异常指标，实现动态图异常检测的无缝集成。实验表明，CLDG与CLDG++在节点分类与动态图异常检测任务中均表现优异；且相比复杂序列模型，CLDG显著降低时空开销，具备高效性。
原文摘要 · Abstract (English)
The rich information underlying graphs has inspired further investigation of unsupervised graph representation. Existing studies mainly depend on node features and topological properties within static graphs to create self-supervised signals, neglecting the temporal components carried by real-world graph data, such as timestamps of edges. To overcome this limitation, this paper explores how to model temporal evolution on dynamic graphs elegantly. Specifically, we introduce a new inductive bias, namely temporal translation invariance, which illustrates the tendency of the identical node to keep similar labels across different timespans. Based on this assumption, we develop a dynamic graph representation framework CLDG that encourages the node to maintain locally consistent temporal translation invariance through contrastive learning on different timespans. Except for standard CLDG which only considers explicit topological links, our further proposed CLDG++ additionally employs graph diffusion to uncover global contextual correlations between nodes, and designs a multi-scale contrastive learning objective composed of local-local, local-global, and global-global contrasts to enhance representation capabilities. Interestingly, by measuring the consistency between different timespans to shape anomaly indicators, CLDG and CLDG++ are seamlessly integrated with the task of spotting anomalies on dynamic graphs, which has broad applications in many high-impact domains, such as finance, cybersecurity, and healthcare. Experiments demonstrate that CLDG and CLDG++ both exhibit desirable performance in downstream tasks including node classification and dynamic graph anomaly detection. Moreover, CLDG significantly reduces time and space complexity by implicitly exploiting temporal cues instead of complicated sequence models.
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。