A Differential Smoothness-based Compact-Dynamic Graph Convolutional Network for Spatiotemporal Signal Recovery

TL;DR

This paper introduces a novel compact-dynamic graph convolutional network that simultaneously captures spatiotemporal correlations and reduces noise interference, significantly improving signal recovery accuracy in real-world applications.

Contribution

It proposes a unified tensor graph convolution framework using tensor M-product and a differential smoothness-based objective function for enhanced spatiotemporal signal recovery.

Findings

Outperforms state-of-the-art models in recovery accuracy

Effectively captures complex spatiotemporal correlations

Reduces noise interference in signals

Abstract

High quality spatiotemporal signal is vitally important for real application scenarios like energy management, traffic planning and cyber security. Due to the uncontrollable factors like abrupt sensors breakdown or communication fault, the spatiotemporal signal collected by sensors is always incomplete. A dynamic graph convolutional network (DGCN) is effective for processing spatiotemporal signal recovery. However, it adopts a static GCN and a sequence neural network to explore the spatial and temporal patterns, separately. Such a separated two-step processing is loose spatiotemporal, thereby failing to capture the complex inner spatiotemporal correlation. To address this issue, this paper proposes a Compact-Dynamic Graph Convolutional Network (CDGCN) for spatiotemporal signal recovery with the following two-fold ideas: a) leveraging the tensor M-product to build a unified tensor graph convolution framework, which considers both spatial and temporal patterns simultaneously; and b) constructing a differential smoothness-based objective function to reduce the noise interference in spatiotemporal signal, thereby further improve the recovery accuracy. Experiments on real-world spatiotemporal datasets demonstrate that the proposed CDGCN significantly outperforms the state-of-the-art models in terms of recovery accuracy.