ScholarMate
English简体中文繁體中文
客服热线:400-1616-289
登录注册
期刊论文

DNformer: Temporal Link Prediction with Transfer Learning in Dynamic Networks

Jiang, Xin; Yu, Zhengxin; Hai, Chao; Liu, Hongbo*; Wu, Xindong; Ward, Tomas1
ACM Transactions on Knowledge Discovery from Data2022-4DOI: 10.1145/3551892
11阅读
引用收藏
分享

摘要

Temporal link prediction (TLP) is among the most important graph learning tasks, capable of predicting dynamic, time-varying links within networks. The key problem of TLP is how to explore potential link-evolving tendency from the increasing number of links over time. There exist three major challenges toward solving this problem: temporal nonlinear sparsity, weak serial correlation, and discontinuous structural dynamics. In this article, we propose a novel transfer learning model, called DNformer, to predict temporal link sequence in dynamic networks. The structural dynamic evolution is sequenced into consecutive links one by one over time to inhibit temporal nonlinear sparsity. The self-attention of the model is used to capture the serial correlation between the input and output link sequences. Moreover, our structural encoding is designed to obtain changing structures from the consecutive links and to learn the mapping between link sequences. This structural encoding consists of two parts: the node clustering encoding of each link and the link similarity encoding between links. These encodings enable the model to perceive the importance and correlation of links. Furthermore, we introduce a measurement of structural similarity in the loss function for the structural differences of link sequences. The experimental results demonstrate that our model outperforms other state-of-the-art TLP methods such as Transformer, TGAT, and EvolveGCN. It achieves the three highest AUC and four highest precision scores in five different representative dynamic networks problems.

学科与关键词

关键词
Dynamic networktransfer learningtemporal link predictionself-attention
相关
加载中…

文献加载失败,请重试

重试

发表信息

论文状态
公开发表
期刊
ACM Transactions on Knowledge Discovery from Data
发表日期
2022-04
卷期
第 17 卷, 第 3 期
DOI
10.1145/3551892
语言
ENGLISH
期刊等级
3区
成果收录
SCIE
资助标注
National Natural Science Foundation of China [91746209, 61772102, 62176036]; Science Foundation Ireland [SFI/12/RC/2289_P2]; Liaoning Collaborative Fund [2020-HYLH-17]

作者

  • J

    Jiang, Xin (第一作者)

    1 · dalian maritime univ

  • Y

    Yu, Zhengxin

查看全部 6 位作者收起作者
  • H

    Hai, Chao

    1 · dalian maritime univ

  • L

    Liu, Hongbo (通讯)

    1 · dalian maritime univ

  • W

    Wu, Xindong

  • W

    Ward, Tomas

登录解锁更多功能

  • 收藏这篇,随时在“我的 · 收藏”找回
  • 认领你的成果,生成推广素材
  • 关注作者获取最新成果
  • 加入项目组、协同写作
注册 / 登录

产品服务

  • 科研之友
  • 创新城
  • 科创云

服务支持

  • 帮助中心
  • 隐私政策
  • 服务条款

联系方式

在线客服:【】
客服热线:400-1616-289
电子邮箱:support@scholarmate.com

关注或下载科研之友

微信二维码
微信公众号
客户端下载二维码
下载客户端
科研成果科研人员科研机构科研动态爱瑞思软件

©2026 深圳市科研之友网络服务有限公司

公安备案图标粤公网安备 44030502000213
粤ICP备 16046710 号粤B2-20110417