Refining Latent Representations: A Generative SSL Approach for Heterogeneous Graph Learning

arXiv:2310.11102v4 Announce Type: replace
Abstract: Self-Supervised Learning (SSL) has shown significant potential and has garnered increasing interest in graph learning. However, particularly for generative SSL methods, its potential in Heterogeneous Graph Learning (HGL) remains relatively underexplored. Generative SSL utilizes an encoder to map the input graph into a latent representation and a decoder to recover the input graph from the latent representation. Previous HGL SSL methods generally design complex strategies to capture graph heterogeneity, which heavily rely on contrastive view …

abstract arxiv cs.ai cs.lg encoder generative graph graph learning however map self-supervised learning ssl supervised learning type