Show simple item record

dc.contributor.authorOpolka, Felix Len
dc.contributor.authorSolomon, Aaronen
dc.contributor.authorCangea, Cătălinaen
dc.contributor.authorVeličković, Petaren
dc.contributor.authorLio, Pietroen
dc.contributor.authorHjelm, R Devonen
dc.date.accessioned2019-06-14T14:30:04Z
dc.date.available2019-06-14T14:30:04Z
dc.identifier.urihttps://www.repository.cam.ac.uk/handle/1810/293629
dc.description.abstractSpatio-temporal graphs such as traffic networks or gene regulatory systems present challenges for the existing deep learning methods due to the complexity of structural changes over time. To address these issues, we introduce Spatio-Temporal Deep Graph Infomax (STDGI)---a fully unsupervised node representation learning approach based on mutual information maximization that exploits both the temporal and spatial dynamics of the graph. Our model tackles the challenging task of node-level regression by training embeddings to maximize the mutual information between patches of the graph, at any given time step, and between features of the central nodes of patches, in the future. We demonstrate through experiments and qualitative studies that the learned representations can successfully encode relevant information about the input graph and improve the predictive performance of spatio-temporal auto-regressive forecasting models.
dc.subjectcs.LGen
dc.subjectcs.LGen
dc.subjectstat.MLen
dc.titleSpatio-Temporal Deep Graph Infomaxen
dc.typeConference Object
dc.identifier.doi10.17863/CAM.40745
rioxxterms.versionAM*
rioxxterms.licenseref.urihttp://www.rioxx.net/licenses/all-rights-reserveden
dc.contributor.orcidLio, Pietro [0000-0002-0540-5053]
rioxxterms.typeConference Paper/Proceeding/Abstracten


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record