Information Decomposition based on Cooperative Game Theory

TL;DR

This paper introduces a novel information decomposition method based on cooperative game theory, providing a more parsimonious and axiom-compliant way to quantify contributions of source variables to mutual information.

Contribution

It proposes a new decomposition approach using cooperative game theory, differing from PID, with fewer terms and improved adherence to key axioms.

Findings

Decomposition assigns fair mutual information shares to source combinations.

The method satisfies local positivity and identity axioms.

It simplifies the information structure by removing redundancy terms.

Abstract

We offer a new approach to the information decomposition problem in information theory: given a 'target' random variable co-distributed with multiple 'source' variables, how can we decompose the mutual information into a sum of non-negative terms that quantify the contributions of each random variable, not only individually but also in combination? We derive our composition from cooperative game theory. It can be seen as assigning a "fair share" of the mutual information to each combination of the source variables. Our decomposition is based on a different lattice from the usual 'partial information decomposition' (PID) approach, and as a consequence our decomposition has a smaller number of terms: it has analogs of the synergy and unique information terms, but lacks terms corresponding to redundancy. Because of this, it is able to obey equivalents of the axioms known as 'local positivity' and 'identity', which cannot be simultaneously satisfied by a PID measure.