FC-GAGA: Fully Connected Gated Graph Architecture for Spatio-Temporal Traffic Forecasting
This addresses traffic management and related applications by providing a graph-agnostic forecasting method, though it appears incremental as it builds on existing fully connected architectures.
The paper tackles traffic forecasting without requiring a known graph structure by introducing a learnable fully connected hard graph gating mechanism, achieving competitive or better performance than existing algorithms on two public datasets.
Forecasting of multivariate time-series is an important problem that has applications in traffic management, cellular network configuration, and quantitative finance. A special case of the problem arises when there is a graph available that captures the relationships between the time-series. In this paper we propose a novel learning architecture that achieves performance competitive with or better than the best existing algorithms, without requiring knowledge of the graph. The key element of our proposed architecture is the learnable fully connected hard graph gating mechanism that enables the use of the state-of-the-art and highly computationally efficient fully connected time-series forecasting architecture in traffic forecasting applications. Experimental results for two public traffic network datasets illustrate the value of our approach, and ablation studies confirm the importance of each element of the architecture. The code is available here: https://github.com/boreshkinai/fc-gaga.