2 papers
cs.LG2025
IMPA-HGAE:Intra-Meta-Path Augmented Heterogeneous Graph Autoencoder
Di Lin, Wanjing Ren, Xuanbin Li +1
Self-supervised learning (SSL) methods have been increasingly applied to diverse downstream tasks due to their superior generalization capabilities and low annotation costs. Howeve…
cs.LG2025
Learning Robust Heterogeneous Graph Representations via Contrastive-Reconstruction under Sparse Semantics
Di Lin, Wanjing Ren, Xuanbin Li +1
In graph self-supervised learning, masked autoencoders (MAE) and contrastive learning (CL) are two prominent paradigms. MAE focuses on reconstructing masked elements, while CL maxi…