A Deep Contrastive Framework for Unsupervised Temporal Link Prediction in Dynamic Networks

链接(几何体) 计算机科学 人工智能 自然语言处理 计算机网络
作者
Pengfei Jiao,Xinxun Zhang,Zehao Liu,Long Zhang,Huaming Wu,Mengzhou Gao,Tianpeng Li,Jian Wu
出处
期刊:Information Sciences [Elsevier BV]
卷期号:667: 120499-120499 被引量:1
标识
DOI:10.1016/j.ins.2024.120499
摘要

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.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
2秒前
时尚俊驰发布了新的文献求助10
2秒前
3秒前
文献发布了新的文献求助30
4秒前
7秒前
我嘞个豆完成签到,获得积分10
7秒前
爱笑晓曼发布了新的文献求助10
8秒前
wdy111应助sc采纳,获得20
8秒前
敏感初露发布了新的文献求助10
8秒前
隐形曼青应助机智思真采纳,获得10
11秒前
思源应助时尚俊驰采纳,获得10
11秒前
可爱的函函应助敏感初露采纳,获得10
11秒前
12秒前
爆米花应助橙子采纳,获得10
15秒前
量子星尘发布了新的文献求助10
17秒前
阿满完成签到 ,获得积分10
18秒前
王馨雨完成签到,获得积分10
19秒前
在水一方应助袁涛采纳,获得10
19秒前
爱笑晓曼完成签到,获得积分10
22秒前
23秒前
24秒前
nuoran发布了新的文献求助10
25秒前
25秒前
乐乐宝完成签到,获得积分10
26秒前
27秒前
彭于晏应助阿钉采纳,获得10
28秒前
孙燕应助阿钉采纳,获得10
28秒前
整齐小松鼠应助阿钉采纳,获得10
28秒前
jszhoucl发布了新的文献求助10
29秒前
一定行发布了新的文献求助10
29秒前
jxlu发布了新的文献求助10
30秒前
32秒前
橙子发布了新的文献求助10
32秒前
科研通AI5应助科研通管家采纳,获得10
33秒前
李健应助科研通管家采纳,获得10
33秒前
爆米花应助科研通管家采纳,获得10
33秒前
乐乐应助科研通管家采纳,获得10
33秒前
天天快乐应助科研通管家采纳,获得10
33秒前
科研通AI2S应助科研通管家采纳,获得10
33秒前
CipherSage应助科研通管家采纳,获得10
34秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
‘Unruly’ Children: Historical Fieldnotes and Learning Morality in a Taiwan Village (New Departures in Anthropology) 400
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
基于可调谐半导体激光吸收光谱技术泄漏气体检测系统的研究 350
Robot-supported joining of reinforcement textiles with one-sided sewing heads 320
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3989378
求助须知:如何正确求助?哪些是违规求助? 3531442
关于积分的说明 11254002
捐赠科研通 3270126
什么是DOI,文献DOI怎么找? 1804887
邀请新用户注册赠送积分活动 882087
科研通“疑难数据库(出版商)”最低求助积分说明 809173