Dyn-GWN: Time-Series Forecasting using Time-varying Graphs with Applications to Finance and Traffic Prediction
Name
3604237.3626864.pdf
Size
806.63 KB
Format
Adobe PDF
Checksum (MD5)
17df2b5eb3f64e0cf4ffecd20a6b9c15
Author(s)
Ibrahim, Shibal
Tell, Max
Mazumder, Rahul
Date Issued
November 27, 2023
Publisher
ACM|4th ACM International Conference on AI in Finance
Citation
Ibrahim, Shibal, Tell, Max and Mazumder, Rahul. 2023. "Dyn-GWN: Time-Series Forecasting using Time-varying Graphs with Applications to Finance and Traffic Prediction."
Version
Final published version
Abstract
Spatio-temporal modeling is an essential lens to understand many real-world phenomena from traffic to finance. There has been exciting work that explores spatio-temporal modeling with temporal graph convolutional networks. Often these methods assume that the spatial structure is static. We propose a new model Dyn-GWN for spatio-temporal learning from time-varying graphs. Our model relies on a novel module called the Tensor Graph Convolutional Module (TGCM), which captures dynamic trends in graphs effectively in the time-varying graph representations. This module has two components: (i) it applies temporal dilated convolutions both on the time-varying graph adjacency space and the time-varying features. (ii) it aggregates the higher-level latent representations from both time-varying components through a proposed layer TGCL. Experiments demonstrate the efficacy of these model across time-series data from finance and traffic domains. Dyn-GWN can give up to better out-of-sample performance than prior methods that learn from time-varying graphs, e.g., EvolveGCN and TM-GCN. Interestingly, Dyn-GWN can be ∼ 300 × faster than EvolveGCN, which is the more competitive baseline from state-of-the-art models that cater to time-varying graphs.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Center for Brains, Minds, and Machines
Sloan School of Management
Terms of Use
Creative Commons Attribution
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1145/3604237.3626864
