Sub-Graph Learning for Spatiotemporal Forecasting via Knowledge Distillation

TL;DR

This paper introduces KD-SGL, a framework that partitions large graphs into sub-graphs and employs both global and local models to improve spatiotemporal forecasting accuracy efficiently.

Contribution

The paper proposes a novel sub-graph learning framework with knowledge distillation, enhancing model performance while reducing complexity compared to ensemble methods.

Findings

Improves spatiotemporal forecasting accuracy.

Achieves comparable results to ensemble models with less complexity.

Effective sub-graph partitioning enhances learning process.

Abstract

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.