The Third Pillar of Causal Analysis? A Measurement Perspective on Causal Representations

TL;DR

This paper introduces a measurement model framework for causal representation learning, proposing a new score to evaluate the usefulness of learned representations for causal reasoning in complex, real-world data.

Contribution

It reinterprets causal representation learning through a measurement lens and introduces T-MEX, a principled score for assessing representation quality for causal tasks.

Findings

T-MEX effectively evaluates learned representations across diverse scenarios.

The framework clarifies conditions for representations to support causal reasoning.

Validation on simulations and ecological videos demonstrates practical utility.

Abstract

Causal reasoning and discovery, two fundamental tasks of causal analysis, often face challenges in applications due to the complexity, noisiness, and high-dimensionality of real-world data. Despite recent progress in identifying latent causal structures using causal representation learning (CRL), what makes learned representations useful for causal downstream tasks and how to evaluate them are still not well understood. In this paper, we reinterpret CRL using a measurement model framework, where the learned representations are viewed as proxy measurements of the latent causal variables. Our approach clarifies the conditions under which learned representations support downstream causal reasoning and provides a principled basis for quantitatively assessing the quality of representations using a new Test-based Measurement EXclusivity (T-MEX) score. We validate T-MEX across diverse causal inference scenarios, including numerical simulations and real-world ecological video analysis, demonstrating that the proposed framework and corresponding score effectively assess the identification of learned representations and their usefulness for causal downstream tasks.