Spatio-Temporal Deep Graph Infomax
View / Open Files
Authors
Opolka, Felix L
Solomon, Aaron
Cangea, Cătălina
Veličković, Petar
Hjelm, R Devon
Type
Conference Object
This Version
AM
Metadata
Show full item recordCitation
Opolka, F. L., Solomon, A., Cangea, C., Veličković, P., Lio, P., & Hjelm, R. D. Spatio-Temporal Deep Graph Infomax. https://doi.org/10.17863/CAM.40745
Abstract
Spatio-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.
Keywords
cs.LG, cs.LG, stat.ML
Identifiers
This record's DOI: https://doi.org/10.17863/CAM.40745
This record's URL: https://www.repository.cam.ac.uk/handle/1810/293629
Rights
Licence:
http://www.rioxx.net/licenses/all-rights-reserved