Dynamic heterogeneous graph representation via contrastive learning based on multi-prior tasks
Authors:
- Wenhao BaiWBWenhao Bai
- Liqing QiuLQLiqing Qiu
- Weidong ZhaoWZWeidong Zhao
- 13 January 2025
- journal article
- research article
- Published by Elsevier in Expert Systems with Applications
- Vol. 269
Abstract
No abstract availableKeywords
Funding Information
- Shandong Province Natural Science Foundation
This publication has 19 references indexed in Scilit:
- KPI-HGNN: Key provenance identification based on a heterogeneous graph neural network for big data access controlInformation Sciences, 2023
- An obstacle avoidance-specific reinforcement learning method based on fuzzy attention mechanism and heterogeneous graph neural networksEngineering Applications of Artificial Intelligence, 2023
- Heterogeneous graph knowledge distillation neural network incorporating multiple relations and cross-semantic interactionsInformation Sciences, 2023
- Self-supervised Dynamic Graph Embedding with evolutionary neighborhood and communityExpert Systems with Applications, 2023
- Line graph contrastive learning for link predictionPattern Recognition, 2023
- Dynamic heterogeneous graph representation learning with neighborhood type modelingNeurocomputing, 2023
- Heterogeneous graph embedding by aggregating meta-path and meta-structure through attention mechanismNeurocomputing, 2022
- iBridge: Inferring bridge links that diffuse information across communitiesKnowledge-Based Systems, 2020
- Patterns and dynamics of users' behavior and interaction: Network analysis of an online communityJournal of the American Society for Information Science and Technology, 2009
- Legislative cosponsorship networks in the US House and SenateSocial Networks, 2006