Enhancing Cross-domain Link Prediction via Evolution Process Modeling
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866929698479538176 |
|---|---|
| author | Huang, Xuanwen Chow, Wei Zhu, Yize Wang, Yang Chai, Ziwei Wang, Chunping Chen, Lei Yang, Yang |
| author_facet | Huang, Xuanwen Chow, Wei Zhu, Yize Wang, Yang Chai, Ziwei Wang, Chunping Chen, Lei Yang, Yang |
| contents | This work proposes DyExpert, a dynamic graph model for cross-domain link prediction. It can explicitly model historical evolving processes to learn the evolution pattern of a specific downstream graph and subsequently make pattern-specific link predictions. DyExpert adopts a decode-only transformer and is capable of efficiently parallel training and inference by \textit{conditioned link generation} that integrates both evolution modeling and link prediction. DyExpert is trained by extensive dynamic graphs across diverse domains, comprising 6M dynamic edges. Extensive experiments on eight untrained graphs demonstrate that DyExpert achieves state-of-the-art performance in cross-domain link prediction. Compared to the advanced baseline under the same setting, DyExpert achieves an average of 11.40% improvement Average Precision across eight graphs. More impressive, it surpasses the fully supervised performance of 8 advanced baselines on 6 untrained graphs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_02168 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Enhancing Cross-domain Link Prediction via Evolution Process Modeling Huang, Xuanwen Chow, Wei Zhu, Yize Wang, Yang Chai, Ziwei Wang, Chunping Chen, Lei Yang, Yang Machine Learning Artificial Intelligence Social and Information Networks This work proposes DyExpert, a dynamic graph model for cross-domain link prediction. It can explicitly model historical evolving processes to learn the evolution pattern of a specific downstream graph and subsequently make pattern-specific link predictions. DyExpert adopts a decode-only transformer and is capable of efficiently parallel training and inference by \textit{conditioned link generation} that integrates both evolution modeling and link prediction. DyExpert is trained by extensive dynamic graphs across diverse domains, comprising 6M dynamic edges. Extensive experiments on eight untrained graphs demonstrate that DyExpert achieves state-of-the-art performance in cross-domain link prediction. Compared to the advanced baseline under the same setting, DyExpert achieves an average of 11.40% improvement Average Precision across eight graphs. More impressive, it surpasses the fully supervised performance of 8 advanced baselines on 6 untrained graphs. |
| title | Enhancing Cross-domain Link Prediction via Evolution Process Modeling |
| topic | Machine Learning Artificial Intelligence Social and Information Networks |
| url | https://arxiv.org/abs/2402.02168 |