INCREASE: Inductive Graph Representation Learning for Spatio-Temporal Kriging

TL;DR

This paper introduces INCREASE, an inductive graph learning model for spatio-temporal kriging that effectively predicts unobserved data points by modeling heterogeneous spatial relations and temporal patterns, outperforming existing methods.

Contribution

The paper presents a novel inductive graph representation learning approach that encodes multiple spatial relations and employs relation-aware GRUs and attention mechanisms for improved spatio-temporal kriging.

Findings

Outperforms state-of-the-art methods on real-world datasets.

More effective when fewer observed locations are available.

Successfully models heterogeneous spatial and temporal dependencies.

Abstract

Spatio-temporal kriging is an important problem in web and social applications, such as Web or Internet of Things, where things (e.g., sensors) connected into a web often come with spatial and temporal properties. It aims to infer knowledge for (the things at) unobserved locations using the data from (the things at) observed locations during a given time period of interest. This problem essentially requires \emph{inductive learning}. Once trained, the model should be able to perform kriging for different locations including newly given ones, without retraining. However, it is challenging to perform accurate kriging results because of the heterogeneous spatial relations and diverse temporal patterns. In this paper, we propose a novel inductive graph representation learning model for spatio-temporal kriging. We first encode heterogeneous spatial relations between the unobserved and observed locations by their spatial proximity, functional similarity, and transition probability. Based on each relation, we accurately aggregate the information of most correlated observed locations to produce inductive representations for the unobserved locations, by jointly modeling their similarities and differences. Then, we design relation-aware gated recurrent unit (GRU) networks to adaptively capture the temporal correlations in the generated sequence representations for each relation. Finally, we propose a multi-relation attention mechanism to dynamically fuse the complex spatio-temporal information at different time steps from multiple relations to compute the kriging output. Experimental results on three real-world datasets show that our proposed model outperforms state-of-the-art methods consistently, and the advantage is more significant when there are fewer observed locations. Our code is available at https://github.com/zhengchuanpan/INCREASE.