New Frontiers in Graph Autoencoders: Joint Community Detection and Link Prediction
원문 초록
Graph autoencoders (GAE) and variational graph autoencoders (VGAE) emerged as powerful methods for link prediction (LP). Their performances are less impressive on community detection (CD), where they are often outperformed by simpler alternatives such as the Louvain method. It is still unclear to what extent one can improve CD with GAE and VGAE, especially in the absence of node features. It is moreover uncertain whether one could do so while simultaneously preserving good performances on LP in a multi-task setting. In this workshop paper, summarizing results from our journal publication (Salha-Galvan et al. 2022), we show that jointly addressing these two tasks with high accuracy is possible. For this purpose, we introduce a community-preserving message passing scheme, doping our GAE and VGAE encoders by considering both the initial graph and Louvain-based prior communities when computing embedding spaces. Inspired by modularity-based clustering, we further propose novel training and optimization strategies specifically designed for joint LP and CD. We demonstrate the empirical effectiveness of our approach, referred to as Modularity-Aware GAE and VGAE, on various real-world graphs.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
How Low Can You Go? Searching for the Intrinsic Dimensionality of Complex Networks using Metric Node Embeddings
Unified Graph Networks (UGN): A Deep Neural Framework for Solving Graph Problems
Large Language Models Meet Graph Neural Networks: A Perspective of Graph Mining
Representation learning of dynamic networks
Multi-Scale Node Embeddings for Graph Modeling and Generation
Hierarchical-Graph-Structured Edge Partition Models for Learning Evolving Community Structure
토론
이 논문과 연결된 포럼 글이 아직 없습니다.