GSA-Forecaster: Forecasting Graph-Based Time-Dependent Data with Graph Sequence Attention
Li, Yang, Wang, Di, Moura, José M. F.
–arXiv.org Artificial Intelligence
Forecasting graph-based time-dependent data has many practical applications. This task is challenging as models need not only to capture spatial dependency and temporal dependency within the data, but also to leverage useful auxiliary information for accurate predictions. In this paper, we analyze limitations of state-of-the-art models on dealing with temporal dependency. To address this limitation, we propose GSA-Forecaster, a new deep learning model for forecasting graph-based time-dependent data. GSA-Forecaster leverages graph sequence attention (GSA), a new attention mechanism proposed in this paper, for effectively capturing temporal dependency. GSA-Forecaster embeds the graph structure of the data into its architecture to address spatial dependency. GSA-Forecaster also accounts for auxiliary information to further improve predictions. We evaluate GSA-Forecaster with large-scale real-world graph-based time-dependent data and demonstrate its effectiveness over state-of-the-art models with 6.7% RMSE and 5.8% MAPE reduction.
arXiv.org Artificial Intelligence
Apr-12-2021
- Country:
- North America > United States
- New York (0.29)
- Pennsylvania > Allegheny County
- Pittsburgh (0.14)
- North America > United States
- Genre:
- Research Report (1.00)
- Industry:
- Technology: