Sub-Graph Learning for Spatiotemporal Forecasting via Knowledge Distillation
This work addresses spatiotemporal forecasting in large graphs, offering an incremental improvement by reducing complexity while maintaining performance.
The paper tackles the challenge of learning diverse patterns in large graphs for spatiotemporal forecasting by proposing KD-SGL, a framework that uses knowledge distillation to divide the graph into sub-graphs with global and local models, improving state-of-the-art performance with comparable results to ensemble models but less complexity.
One of the challenges in studying the interactions in large graphs is to learn their diverse pattern and various interaction types. Hence, considering only one distribution and model to study all nodes and ignoring their diversity and local features in their neighborhoods, might severely affect the overall performance. Based on the structural information of the nodes in the graph and the interactions between them, the main graph can be divided into multiple sub-graphs. This graph partitioning can tremendously affect the learning process, however the overall performance is highly dependent on the clustering method to avoid misleading the model. In this work, we present a new framework called KD-SGL to effectively learn the sub-graphs, where we define one global model to learn the overall structure of the graph and multiple local models for each sub-graph. We assess the performance of the proposed framework and evaluate it on public datasets. Based on the achieved results, it can improve the performance of the state-of-the-arts spatiotemporal models with comparable results compared to ensemble of models with less complexity.