Manifold structure in graph embeddings

Research output: Contribution to conferenceConference Paperpeer-review


Statistical analysis of a graph often starts with embedding, the process of representing its nodes as points in space. How to choose the embedding dimension is a nuanced decision in practice, but in theory a notion of true dimension is often available. In spectral embedding, this dimension may be very high. However, this paper shows that existing random graph models, including graphon and other latent position models, predict the data should live near a much lower-dimensional set. One may therefore circumvent the curse of dimensionality by employing methods which exploit hidden manifold structure.
Original languageEnglish
Publication statusAccepted/In press - 2020
EventNeural Information Processing Systems (NeurIPS) - Virtual-only
Duration: 6 Dec 202012 Dec 2020


ConferenceNeural Information Processing Systems (NeurIPS)


Dive into the research topics of 'Manifold structure in graph embeddings'. Together they form a unique fingerprint.

Cite this