<ul><li>IMP-HGAE is a novel framework designed to improve target node embeddings by leveraging internal node information along meta-paths in heterogeneous graphs.</li><li>This approach addresses the limitation of existing models that only utilize information from nodes at the ends of meta-paths.</li><li>IMPA-HGAE has shown superior performance on heterogeneous datasets and introduces masking strategies to enhance generative SSL models on heterogeneous graph data.</li><li>The paper also discusses interpretability of the method and potential future directions for generative self-supervised learning in heterogeneous graphs.</li></ul>

IMPA-HGAE:Intra-Meta-Path Augmented Heterogeneous Graph Autoencoder

Discover more