A deep contrastive framework for unsupervised temporal link prediction in dynamic networks

In dynamic networks, temporal link prediction aims to predict the appearance and disappearance of links in future snapshots based on the network structure we have observed. It also plays a crucial role in network analysis and predicting the behavior of the dynamic system. However, most existing stud...

Full description

Saved in:
Bibliographic Details
Published in:Information sciences Vol. 667; p. 120499
Main Authors: Jiao, Pengfei, Zhang, Xinxun, Liu, Zehao, Zhang, Long, Wu, Huaming, Gao, Mengzhou, Li, Tianpeng, Wu, Jian
Format: Journal Article
Language:English
Published: Elsevier Inc 01.05.2024
Subjects:
Contrastive learning
Deep learning
Dynamic network
Multi-step prediction
Unsupervised link prediction
Deep learning
Unsupervised link prediction
Dynamic network
Multi-step prediction
Contrastive learning
ISSN:0020-0255
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In dynamic networks, temporal link prediction aims to predict the appearance and disappearance of links in future snapshots based on the network structure we have observed. It also plays a crucial role in network analysis and predicting the behavior of the dynamic system. However, most existing studies only focus on supervised temporal link prediction problems, i.e., taking part of the links in future snapshots as supervised information. The ones that can solve the unsupervised temporal link prediction problem are mainly based on matrix decomposition, which lack the capability to automatically extract nonlinear spatial and temporal features from dynamic networks. The most challenging part of this problem is to extract the inherent evolution of the patterns hidden in dynamic networks in unsupervised ways. Inspired by the application and achievement of contrastive learning in network representation learning, we propose a novel deep Contrastive framework for unsupervised Temporal Link Prediction (CTLP). Our framework is based on a deep encoder-decoder architecture, which can capture the nonlinear structure and temporal features automatically and can predict future links of subsequent snapshots of dynamic networks in an unsupervised manner. Besides, CTLP could handle the multi-step temporal link prediction problem of dynamic networks through attenuation modeling across the snapshots. Extensive experiments on temporal link prediction show that our CTLP framework significantly outperforms state-of-the-art unsupervised methods, and even outperforms the supervised methods in some cases.
ISSN:0020-0255
DOI:10.1016/j.ins.2024.120499