Causal Structure Identification from Corrupt Data-Streams

TL;DR

This paper investigates how corruption in data streams affects the identification of causal structures in complex networks, providing conditions to distinguish true links from spurious ones, applicable to nonlinear and feedback systems.

Contribution

It introduces a necessary and sufficient condition to identify the effects of data corruption on causal inference in dynamic Bayesian networks, including nonlinear and feedback systems.

Findings

Corruption can lead to spurious causal links.

A condition to distinguish true from spurious links is established.

Consistency of the conditional directed information estimator is proven.

Abstract

Complex networked systems can be modeled and represented as graphs, with nodes representing the agents and the links describing the dynamic coupling between them. The fundamental objective of network identification for dynamic systems is to identify causal influence pathways. However, dynamically related data-streams that originate from different sources are prone to corruption caused by asynchronous time stamps, packet drops, and noise. In this article, we show that identifying causal structure using corrupt measurements results in the inference of spurious links. A necessary and sufficient condition that delineates the effects of corruption on a set of nodes is obtained. Our theory applies to nonlinear systems, and systems with feedback loops. Our results are obtained by the analysis of conditional directed information in dynamic Bayesian networks. We provide consistency results for the conditional directed information estimator that we use by showing almost-sure convergence.