One Graph Model for Cross-domain Dynamic Link Prediction

Autor:	Huang, Xuanwen, Chow, Wei, Wang, Yang, Chai, Ziwei, Wang, Chunping, Chen, Lei, Yang, Yang
Rok vydání:	2024
Předmět:	Computer Science - Machine Learning Computer Science - Artificial Intelligence Computer Science - Social and Information Networks
Druh dokumentu:	Working Paper
Popis:	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. Comment: Under review
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2402.02168 Zobrazit plný text záznamu View this record from Arxiv