ST-FiT: Inductive Spatial-Temporal Forecasting with Limited Training Data

TL;DR

This paper introduces ST-FiT, a framework for inductive spatial-temporal forecasting that effectively generalizes to nodes with no available training data by combining data augmentation and topology learning.

Contribution

The paper proposes a novel framework, ST-FiT, enabling spatial-temporal models to generalize to nodes lacking training data, addressing a key real-world challenge.

Findings

ST-FiT improves forecasting accuracy on nodes without training data.

The framework enhances existing STGNNs with minimal additional complexity.

Experimental results show significant performance gains across multiple datasets.

Abstract

Spatial-temporal graphs are widely used in a variety of real-world applications. Spatial-Temporal Graph Neural Networks (STGNNs) have emerged as a powerful tool to extract meaningful insights from this data. However, in real-world applications, most nodes may not possess any available temporal data during training. For example, the pandemic dynamics of most cities on a geographical graph may not be available due to the asynchronous nature of outbreaks. Such a phenomenon disagrees with the training requirements of most existing spatial-temporal forecasting methods, which jeopardizes their effectiveness and thus blocks broader deployment. In this paper, we propose to formulate a novel problem of inductive forecasting with limited training data. In particular, given a spatial-temporal graph, we aim to learn a spatial-temporal forecasting model that can be easily generalized onto those nodes without any available temporal training data. To handle this problem, we propose a principled framework named ST-FiT. ST-FiT consists of two key learning components: temporal data augmentation and spatial graph topology learning. With such a design, ST-FiT can be used on top of any existing STGNNs to achieve superior performance on the nodes without training data. Extensive experiments verify the effectiveness of ST-FiT in multiple key perspectives.