Nov. 17, 2022, 2:11 a.m. | Guillaume Salha-Galvan, Johannes F. Lutzeyer, George Dasoulas, Romain Hennequin, Michalis Vazirgiannis

cs.LG updates on arXiv.org arxiv.org

Graph autoencoders (GAE) and variational graph autoencoders (VGAE) emerged as
powerful methods for link prediction (LP). Their performances are less
impressive on community detection (CD), where they are often outperformed by
simpler alternatives such as the Louvain method. It is still unclear to what
extent one can improve CD with GAE and VGAE, especially in the absence of node
features. It is moreover uncertain whether one could do so while simultaneously
preserving good performances on LP in a multi-task setting. …

arxiv community detection graph link prediction prediction

Lead Developer (AI)

@ Cere Network | San Francisco, US

Research Engineer

@ Allora Labs | Remote

Ecosystem Manager

@ Allora Labs | Remote

Founding AI Engineer, Agents

@ Occam AI | New York

AI Engineer Intern, Agents

@ Occam AI | US

AI Research Scientist

@ Vara | Berlin, Germany and Remote