Saved in:
Bibliographic Details
Main Authors: Zhu, Xiaobo, Wu, Yan, Li, Zhipeng, Su, Hailong, Che, Jin, Chen, Zhanheng, Wang, Liying
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2312.07983
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916220178006016
author Zhu, Xiaobo
Wu, Yan
Li, Zhipeng
Su, Hailong
Che, Jin
Chen, Zhanheng
Wang, Liying
author_facet Zhu, Xiaobo
Wu, Yan
Li, Zhipeng
Su, Hailong
Che, Jin
Chen, Zhanheng
Wang, Liying
contents Recently, representation learning over graph networks has gained popularity, with various models showing promising results. Despite this, several challenges persist: 1) most methods are designed for static or discrete-time dynamic graphs; 2) existing continuous-time dynamic graph algorithms focus on a single evolving perspective; and 3) many continuous-time dynamic graph approaches necessitate numerous temporal neighbors to capture long-term dependencies. In response, this paper introduces the Multi-Perspective Feedback-Attention Coupling (MPFA) model. MPFA incorporates information from both evolving and raw perspectives, efficiently learning the interleaved dynamics of observed processes. The evolving perspective employs temporal self-attention to distinguish continuously evolving temporal neighbors for information aggregation. Through dynamic updates, this perspective can capture long-term dependencies using a small number of temporal neighbors. Meanwhile, the raw perspective utilizes a feedback attention module with growth characteristic coefficients to aggregate raw neighborhood information. Experimental results on a self-organizing dataset and seven public datasets validate the efficacy and competitiveness of our proposed model.
format Preprint
id arxiv_https___arxiv_org_abs_2312_07983
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Multi-perspective Feedback-attention Coupling Model for Continuous-time Dynamic Graphs
Zhu, Xiaobo
Wu, Yan
Li, Zhipeng
Su, Hailong
Che, Jin
Chen, Zhanheng
Wang, Liying
Machine Learning
Artificial Intelligence
Social and Information Networks
Recently, representation learning over graph networks has gained popularity, with various models showing promising results. Despite this, several challenges persist: 1) most methods are designed for static or discrete-time dynamic graphs; 2) existing continuous-time dynamic graph algorithms focus on a single evolving perspective; and 3) many continuous-time dynamic graph approaches necessitate numerous temporal neighbors to capture long-term dependencies. In response, this paper introduces the Multi-Perspective Feedback-Attention Coupling (MPFA) model. MPFA incorporates information from both evolving and raw perspectives, efficiently learning the interleaved dynamics of observed processes. The evolving perspective employs temporal self-attention to distinguish continuously evolving temporal neighbors for information aggregation. Through dynamic updates, this perspective can capture long-term dependencies using a small number of temporal neighbors. Meanwhile, the raw perspective utilizes a feedback attention module with growth characteristic coefficients to aggregate raw neighborhood information. Experimental results on a self-organizing dataset and seven public datasets validate the efficacy and competitiveness of our proposed model.
title Multi-perspective Feedback-attention Coupling Model for Continuous-time Dynamic Graphs
topic Machine Learning
Artificial Intelligence
Social and Information Networks
url https://arxiv.org/abs/2312.07983