2026-09-18T22:52:45Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/1448642022-08-30T03:31:40Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023
Mazumder, Rahul
Tell, Max R.
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
2022-08-29T16:17:06Z
2022-08-29T16:17:06Z
2022-05
2022-05-27T16:19:29.251Z
https://hdl.handle.net/1721.1/144864
Spatio-temporal modeling is an essential lens to understand many real-world phenomena from traffic [20] [10] to epidemiology [12]. Although forecasting time series is an exceptionally well-studied problem, recent years have seen impressive gains in the performance of graph learning as a paradigm for spatial learning problems. Some recent work has explored the intersection of these two fields but often assumes that the underlying graph structure is static. We introduce Dynamic Spatio-Temporal Graph Convolution Network (DST-GCN) as a novel architecture for spatio-temporal modeling with changing graph structure. DST-GCN employs a convolutional architecture to learn spatio-temporal relationships that provide strong generalization and attractive computational efficiency. We provide empirical results for several datasets from different domains that demonstrate the gains provided by DST-GCN.
M.Eng.
Massachusetts Institute of Technology
In Copyright - Educational Use Permitted
Copyright MIT
http://rightsstatements.org/page/InC-EDU/1.0/
Dynamic Spatio-Temporal Graph Convolutional Networks
Thesis
application/pdf
Master
Master of Engineering in Electrical Engineering and Computer Science
Publication
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="8d075f20-8d14-44e6-a2a1-43d4c10bd3a6">
<Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type>
<Title>Dynamic Spatio-Temporal Graph Convolutional Networks</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2022-05</PublicationDate>
<Authors>
<Author>
<DisplayName>Tell, Max R.</DisplayName>
<Affiliation>
<OrgUnit>
</OrgUnit>
</Affiliation>
</Author>
</Authors>
<Editors>
</Editors>
<Publishers>
<Publisher>
<DisplayName>Massachusetts Institute of Technology</DisplayName>
<OrgUnit />
</Publisher>
</Publishers>
<License>http://rightsstatements.org/page/InC-EDU/1.0/</License>
<Abstract>Spatio-temporal modeling is an essential lens to understand many real-world phenomena from traffic [20] [10] to epidemiology [12]. Although forecasting time series is an exceptionally well-studied problem, recent years have seen impressive gains in the performance of graph learning as a paradigm for spatial learning problems. Some recent work has explored the intersection of these two fields but often assumes that the underlying graph structure is static. We introduce Dynamic Spatio-Temporal Graph Convolution Network (DST-GCN) as a novel architecture for spatio-temporal modeling with changing graph structure. DST-GCN employs a convolutional architecture to learn spatio-temporal relationships that provide strong generalization and attractive computational efficiency. We provide empirical results for several datasets from different domains that demonstrate the gains provided by DST-GCN.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>