Abstract
Spatiotemporal data can be represented as a process over a graph, which captures their spatial relationships either explicitly or implicitly. How to leverage such a structure for learning representations is one of the key challenges when working with graphs. In this paper, we represent the spatiotemporal relationships through product graphs and develop a first principle graph-time convolutional neural network (GTCNN). The GTCNN is a compositional architecture with each layer comprising a graph-time convolutional module, a graphtime pooling module, and a nonlinearity. We develop a graph-time convolutional filter by following the shift-and-sum principles of the convolutional operator to learn higher-level features over the product graph. The product graph itself is parametric so that we can learn also the spatiotemporal coupling from data. We develop a zero-pad pooling that preserves the spatial graph (the prior about the data) while reducing the number of active nodes and the parameters. Experimental results with synthetic and real data corroborate the different components and compare with baseline and state-of-the-art solutions.
Original language | English |
---|---|
Title of host publication | 2021 IEEE Data Science and Learning Workshop (DSLW) |
Publisher | IEEE |
Number of pages | 6 |
ISBN (Electronic) | 978-1-6654-2825-5 |
ISBN (Print) | 978-1-6654-2826-2 |
DOIs | |
Publication status | Published - 2021 |
Event | 2021 IEEE Data Science and Learning Workshop, DSLW 2021 - Toronto, Canada Duration: 5 Jun 2021 → 6 Jun 2021 |
Conference
Conference | 2021 IEEE Data Science and Learning Workshop, DSLW 2021 |
---|---|
Country/Territory | Canada |
City | Toronto |
Period | 5/06/21 → 6/06/21 |
Bibliographical note
Accepted author manuscriptKeywords
- Graph neural networks
- Graph signal processing
- Graph-time neural networks
- Spatiotemporal learning