提出自监督方法TiGer，清理动态图中的噪声边，提升节点分类效果。
TiGer: Self-Supervised Purification for Time-evolving Graphs
- 用自注意力捕捉长期上下文，统计距离检测短期异常，双路评分识别噪声边
- 在5个真实数据集上，去噪准确率比现有方法高10.2%，分类性能提升5.3%
- 无需噪声标签，适合处理社交、引用等随时间演化的复杂网络
时间演化图（如社交网络、引文网络）常包含干扰结构与时间模式的噪声，影响下游任务如节点分类。现有净化方法多针对静态图，难以捕捉动态图中的关键时序依赖。本文提出TiGer（Time-evolving Graph purifier），一种专为时间演化图设计的自监督方法。TiGer通过（1）自注意力机制捕捉由远近历史事件共同塑造的长期上下文模式，（2）统计距离度量检测短期不一致性，为边分配两个子得分。基于集成策略筛选可疑（即噪声类）边，实现无标签鲁棒净化。在五个真实数据集上的实验表明，TiGer的去噪准确率比现有最优方法高出最多10.2%，节点分类性能提升最高达5.3%。
原文摘要 · Abstract (English)
Time-evolving graphs, such as social and citation networks, often contain noise that distorts structural and temporal patterns, adversely affecting downstream tasks, such as node classification. Existing purification methods focus on static graphs, limiting their ability to account for critical temporal dependencies in dynamic graphs. In this work, we propose TiGer (Time-evolving Graph purifier), a self-supervised method explicitly designed for time-evolving graphs. TiGer assigns two different sub-scores to edges using (1) self-attention for capturing long-term contextual patterns shaped by both adjacent and distant past events of varying significance and (2) statistical distance measures for detecting inconsistency over a short-term period. These sub-scores are used to identify and filter out suspicious (i.e., noise-like) edges through an ensemble strategy, ensuring robustness without requiring noise labels. Our experiments on five real-world datasets show TiGer filters out noise with up to 10.2% higher accuracy and improves node classification performance by up to 5.3%, compared to state-of-the-art methods.
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。