GKNet: Graph Kalman Filtering and Model Inference via Model-based Deep Learning

TL;DR

This paper introduces GKNet, a graph-aware state space model that combines model-based inference with deep learning to effectively analyze and predict graph-structured time series data.

Contribution

It proposes a novel graph Kalman filtering approach integrated with deep learning for scalable, end-to-end inference on graph time series.

Findings

Effective modeling of graph-temporal data with limited parameters

Improved prediction and imputation accuracy

Scalable deep learning architecture for graph state inference

Abstract

Inference tasks with time series over graphs are of importance in applications such as urban water networks, economics, and networked neuroscience. Addressing these tasks typically relies on identifying a computationally affordable model that jointly captures the graph-temporal patterns of the data. In this work, we propose a graph-aware state space model for graph time series, where both the latent state and the observation equation are parametric graph-induced models with a limited number of parameters that need to be learned. More specifically, we consider the state equation to follow a stochastic partial differential equation driven by noise over the graphs edges accounting not only for potential edge uncertainties but also for increasing the degrees of freedom in the latter in a tractable manner. The graph structure conditioning of the noise dispersion allows the state variable to deviate from the stochastic process in certain neighborhoods. The observation model is a sampled and graph-filtered version of the state capturing multi-hop neighboring influence. The goal is to learn the parameters in both state and observation models from the partially observed data for downstream tasks such as prediction and imputation. The model is inferred first through a maximum likelihood approach that provides theoretical tractability but is limited in expressivity and scalability. To improve on the latter, we use the state-space formulation to build a principled deep learning architecture that jointly learns the parameters and tracks the state in an end-to-end manner in the spirit of Kalman neural networks.