Learning Network Representations with Disentangled Graph Auto-Encoder
D Fan, C Gao - arXiv preprint arXiv:2402.01143, 2024 - arxiv.org
The (variational) graph auto-encoder is extensively employed for learning representations of
graph-structured data. However, the formation of real-world graphs is a complex and …
graph-structured data. However, the formation of real-world graphs is a complex and …
Role-oriented representation learning via fusioning local and higher-order feature
Role-oriented representation learning extracts structural features by capturing the structural
similarities of nodes to generate representations that preserve the structural equivalence …
similarities of nodes to generate representations that preserve the structural equivalence …