TiGer: Self-Supervised Purification for Time-evolving Graphs
This addresses noise purification in dynamic graphs like social networks, offering a novel approach for tasks such as node classification, though it is incremental relative to static graph methods.
The paper tackles noise in time-evolving graphs, which distorts patterns and affects tasks like node classification, by proposing TiGer, a self-supervised purification method that filters out noise with up to 10.2% higher accuracy and improves node classification by up to 5.3% compared to state-of-the-art methods.
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.