TiGer: Self-Supervised Purification for Time-evolving Graphs
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917950874714112 |
|---|---|
| author | Jo, Hyeonsoo Lee, Jongha Bu, Fanchen Shin, Kijung |
| author_facet | Jo, Hyeonsoo Lee, Jongha Bu, Fanchen Shin, Kijung |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_06990 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | TiGer: Self-Supervised Purification for Time-evolving Graphs Jo, Hyeonsoo Lee, Jongha Bu, Fanchen Shin, Kijung Machine Learning 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. |
| title | TiGer: Self-Supervised Purification for Time-evolving Graphs |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2503.06990 |