Show simple item record

dc.contributor.authorCini, Andrea
dc.contributor.authorMarisca, Ivan
dc.contributor.authorBianchi, Filippo Maria
dc.contributor.authorAlippi, Cesare
dc.date.accessioned2023-04-17T08:09:22Z
dc.date.available2023-04-17T08:09:22Z
dc.date.issued2023
dc.description.abstractNeural forecasting of spatiotemporal time series drives both research and industrial innovation in several relevant application domains. Graph neural networks (GNNs) are often the core component of the forecasting architecture. However, in most spatiotemporal GNNs, the computational complexity scales up to a quadratic factor with the length of the sequence times the number of links in the graph, hence hindering the application of these models to large graphs and long temporal sequences. While methods to improve scalability have been proposed in the context of static graphs, few research efforts have been devoted to the spatiotemporal case. To fill this gap, we propose a scalable architecture that exploits an efficient encoding of both temporal and spatial dynamics. In particular, we use a randomized recurrent neural network to embed the history of the input time series into high-dimensional state representations encompassing multi-scale temporal dynamics. Such representations are then propagated along the spatial dimension using different powers of the graph adjacency matrix to generate node embeddings characterized by a rich pool of spatiotemporal features. The resulting node embeddings can be efficiently pre-computed in an unsupervised manner, before being fed to a feed-forward decoder that learns to map the multi-scale spatiotemporal representations to predictions. The training procedure can then be parallelized node-wise by sampling the node embeddings without breaking any dependency, thus enabling scalability to large networks. Empirical results on relevant datasets show that our approach achieves results competitive with the state of the art, while dramatically reducing the computational burden.en_US
dc.descriptionSource at <a href=https://ojs.aaai.org/index.php/AAAI/index>https://ojs.aaai.org/index.php/AAAI/index</a>.en_US
dc.identifier.citationCini, Marisca, Bianchi, Alippi. Scalable Spatiotemporal Graph Neural Networks. Proceedings of the AAAI Conference on Artificial Intelligence. 2023en_US
dc.identifier.cristinIDFRIDAID 2081785
dc.identifier.issn2159-5399
dc.identifier.issn2374-3468
dc.identifier.urihttps://hdl.handle.net/10037/28994
dc.language.isoengen_US
dc.publisherAssociation for the Advancement of Artificial Intelligenceen_US
dc.relation.journalProceedings of the AAAI Conference on Artificial Intelligence
dc.rights.accessRightsopenAccessen_US
dc.rights.holderCopyright 2023 The Author(s)en_US
dc.rights.urihttps://creativecommons.org/licenses/by/4.0en_US
dc.rightsAttribution 4.0 International (CC BY 4.0)en_US
dc.titleScalable Spatiotemporal Graph Neural Networksen_US
dc.type.versionsubmittedVersionen_US
dc.typeJournal articleen_US
dc.typeTidsskriftartikkelen_US


File(s) in this item

Thumbnail

This item appears in the following collection(s)

Show simple item record

Attribution 4.0 International (CC BY 4.0)
Except where otherwise noted, this item's license is described as Attribution 4.0 International (CC BY 4.0)