Graph Representation Learning and its Applications (GRLA 2026)
The 4th workshop on Graph Representation Learning and its Applications, collocated with DSC 2026 in Qingdao, China.
Scope
GRLA 2026 focuses on graph representation learning, especially novel and exciting applications of graph representation learning in different fields.
Graph-structured data is ubiquitous throughout the natural and social sciences, from telecommunication networks to quantum chemistry. Building relational inductive biases into deep learning architectures is crucial for systems that learn, reason, and generalize from relational data. Graphs also provide a powerful data paradigm for organizing, managing, and harnessing intricate data relationships to support advanced AI agents.
Recent research on graph representation learning includes deep graph embeddings, graph neural networks, and neural message-passing approaches. These advances have supported new results in domains such as chemical synthesis, 3D vision, recommender systems, question answering, and social network analysis. GRLA 2026 aims to support community building and discussion in this fast-growing research area.
Topics of Interest
Topics of interest include but are not limited to:
- Unsupervised node representation learning
- Learning representations of entire graphs
- Graph neural networks
- Graph meets AI agent
- Heterogeneous graph embedding
- Knowledge graph embedding
- Graph alignment
- Dynamic graph representation
- Graph representation learning for relational reasoning
- Graph anomaly detection
- Applications in recommender systems
- Applications in information network analysis
- Applications in social network analysis
Paper Submission
All submissions should be written in English and submitted through the workshop submission system. The GRLA 2026 submission-system URL is TBD.
A paper submitted to GRLA 2026 must not be under review for any other conference or journal while it is being considered for GRLA 2026, and must be substantially different from any previously published work. Submissions will be reviewed in a single-blind manner.
Workshop manuscripts should follow the Springer LNCS proceedings format. Accepted and presented workshop papers are planned to be included in the DSC 2026 Springer LNCS proceedings, subject to final proceedings approval and organizer instructions.
- Instructions for Authors (PDF)
- LaTeX2e Proceedings Template (ZIP)
- Microsoft Word Proceedings Template (ZIP)
- Latest Springer LNCS author instructions and templates
Important Dates
- Full paper due: TBD
- Acceptance notification: TBD
- Camera-ready copy: TBD
- Workshop date: September 11-13, 2026
Organization
Workshop General Chairs
- Qianzhen Zhang, National University of Defense Technology, Changsha, China
- Zhaoyun Ding, National University of Defense Technology, Changsha, China
Program Committee
- Lailong Luo, National University of Defense Technology, Changsha, China
- Xianqiang Zhu, National University of Defense Technology, Changsha, China
- Xiaocan Li, Hunan University, Changsha, China
- Mingrui Lao, National University of Defense Technology, Changsha, China
- Yiting Chen, Guilin University of Electronic Technology, Guilin, China
- Shen Zhang, National University of Defense Technology, Changsha, China
- Yan Li, Guilin University of Electronic Technology, Guilin, China
- Xiang Xu, Hangzhou Dianzi University, Hangzhou, China
Contact
For questions about GRLA 2026, please contact Dr. Qianzhen Zhang: zhangqianzhen18@nudt.edu.cn.
