Graph Representation Learning
Graph representation learning aims to encode graph-structured data into low-dimensional vector representations suitable for machine learning tasks. Current research focuses on improving the expressiveness and efficiency of graph neural networks (GNNs), exploring alternative approaches like topological embeddings and leveraging large language models for enhanced interpretability and handling of text-attributed graphs. These advancements are crucial for tackling challenges in various domains, including recommendation systems, anomaly detection, and biological data analysis, where graph-structured data is prevalent and efficient, accurate analysis is critical.
Papers
Mixture of Experts Meets Decoupled Message Passing: Towards General and Adaptive Node Classification
Xuanze Chen, Jiajun Zhou, Shanqing Yu, Qi Xuan
Why Does Dropping Edges Usually Outperform Adding Edges in Graph Contrastive Learning?
Yanchen Xu, Siqi Huang, Hongyuan Zhang, Xuelong Li
Repository-Level Graph Representation Learning for Enhanced Security Patch Detection
Xin-Cheng Wen, Zirui Lin, Cuiyun Gao, Hongyu Zhang, Yong Wang, Qing Liao
Bootstrapping Heterogeneous Graph Representation Learning via Large Language Models: A Generalized Approach
Hang Gao, Chenhao Zhang, Fengge Wu, Junsuo Zhao, Changwen Zheng, Huaping Liu