Initial Results for Pairwise Causal Discovery Using Quantitative Information Flow

TL;DR

This paper explores the use of Quantitative Information Flow as a feature for pairwise causal discovery, showing promising results that are comparable to current state-of-the-art methods and encouraging further research into its causal implications.

Contribution

It introduces the novel application of Quantitative Information Flow for causal discovery, demonstrating its potential as an effective feature in real-world datasets.

Findings

QIF features are statistically comparable to existing methods

QIF shows promise in identifying causal relationships

Initial results motivate further causal analysis with QIF

Abstract

Pairwise Causal Discovery is the task of determining causal, anticausal, confounded or independence relationships from pairs of variables. Over the last few years, this challenging task has promoted not only the discovery of novel machine learning models aimed at solving the task, but also discussions on how learning the causal direction of variables may benefit machine learning overall. In this paper, we show that Quantitative Information Flow (QIF), a measure usually employed for measuring leakages of information from a system to an attacker, shows promising results as features for the task. In particular, experiments with real-world datasets indicate that QIF is statistically tied to the state of the art. Our initial results motivate further inquiries on how QIF relates to causality and what are its limitations.