THeGCN: Temporal Heterophilic Graph Convolutional Network

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yan, Yuchen, Chen, Yuzhong, Chen, Huiyuan, Li, Xiaoting, Xu, Zhe, Zeng, Zhichen, Liu, Lihui, Liu, Zhining, Tong, Hanghang
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915098468024320
author Yan, Yuchen
Chen, Yuzhong
Chen, Huiyuan
Li, Xiaoting
Xu, Zhe
Zeng, Zhichen
Liu, Lihui
Liu, Zhining
Tong, Hanghang
author_facet Yan, Yuchen
Chen, Yuzhong
Chen, Huiyuan
Li, Xiaoting
Xu, Zhe
Zeng, Zhichen
Liu, Lihui
Liu, Zhining
Tong, Hanghang
contents Graph Neural Networks (GNNs) have exhibited remarkable efficacy in diverse graph learning tasks, particularly on static homophilic graphs. Recent attention has pivoted towards more intricate structures, encompassing (1) static heterophilic graphs encountering the edge heterophily issue in the spatial domain and (2) event-based continuous graphs in the temporal domain. State-of-the-art (SOTA) has been concurrently addressing these two lines of work but tends to overlook the presence of heterophily in the temporal domain, constituting the temporal heterophily issue. Furthermore, we highlight that the edge heterophily issue and the temporal heterophily issue often co-exist in event-based continuous graphs, giving rise to the temporal edge heterophily challenge. To tackle this challenge, this paper first introduces the temporal edge heterophily measurement. Subsequently, we propose the Temporal Heterophilic Graph Convolutional Network (THeGCN), an innovative model that incorporates the low/high-pass graph signal filtering technique to accurately capture both edge (spatial) heterophily and temporal heterophily. Specifically, the THeGCN model consists of two key components: a sampler and an aggregator. The sampler selects events relevant to a node at a given moment. Then, the aggregator executes message-passing, encoding temporal information, node attributes, and edge attributes into node embeddings. Extensive experiments conducted on 5 real-world datasets validate the efficacy of THeGCN.
format Preprint
id arxiv_https___arxiv_org_abs_2412_16435
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle THeGCN: Temporal Heterophilic Graph Convolutional Network
Yan, Yuchen
Chen, Yuzhong
Chen, Huiyuan
Li, Xiaoting
Xu, Zhe
Zeng, Zhichen
Liu, Lihui
Liu, Zhining
Tong, Hanghang
Machine Learning
Information Retrieval
Social and Information Networks
Graph Neural Networks (GNNs) have exhibited remarkable efficacy in diverse graph learning tasks, particularly on static homophilic graphs. Recent attention has pivoted towards more intricate structures, encompassing (1) static heterophilic graphs encountering the edge heterophily issue in the spatial domain and (2) event-based continuous graphs in the temporal domain. State-of-the-art (SOTA) has been concurrently addressing these two lines of work but tends to overlook the presence of heterophily in the temporal domain, constituting the temporal heterophily issue. Furthermore, we highlight that the edge heterophily issue and the temporal heterophily issue often co-exist in event-based continuous graphs, giving rise to the temporal edge heterophily challenge. To tackle this challenge, this paper first introduces the temporal edge heterophily measurement. Subsequently, we propose the Temporal Heterophilic Graph Convolutional Network (THeGCN), an innovative model that incorporates the low/high-pass graph signal filtering technique to accurately capture both edge (spatial) heterophily and temporal heterophily. Specifically, the THeGCN model consists of two key components: a sampler and an aggregator. The sampler selects events relevant to a node at a given moment. Then, the aggregator executes message-passing, encoding temporal information, node attributes, and edge attributes into node embeddings. Extensive experiments conducted on 5 real-world datasets validate the efficacy of THeGCN.
title THeGCN: Temporal Heterophilic Graph Convolutional Network
topic Machine Learning
Information Retrieval
Social and Information Networks
url https://arxiv.org/abs/2412.16435