GeoGAE: Scalable Graph-Level Autoencoding via Hyperball Cloud Representations
This work proposes GeoGAE, an autoencoder, in which the Transformer encoder translates a hyperball cloud into a graph-level embedding, and the Transformer decoder translates the graph-level embedding back into the graph.
Radosław P. Nowak, Anna Bielawska, B. Stefańczyk et al.
· 0 citations