用测量理论评估因果表示质量，提升其在真实场景中的可信度。
The Third Pillar of Causal Analysis? A Measurement Perspective on Causal Representations
- 将因果表示视为潜变量的代理测量，构建可解释框架
- 提出T-MEX评分，量化表示对因果推理的支撑能力
- 在模拟与生态视频数据中验证，适合做因果表示评估的研究者
因果推理与发现是因果分析的核心任务，但在实际应用中常因数据复杂、噪声多、维度高而面临挑战。尽管因果表示学习（CRL）在识别潜在因果结构方面取得进展，但所学表示为何能支持下游因果任务，以及如何评估其质量仍不明确。本文从测量模型视角重释CRL，将学习到的表示视为潜变量的代理测量。该框架明确了表示支持因果推理的前提条件，并提出基于测试的测量独占性（T-MEX）评分，为表示质量提供定量评估依据。我们在多种因果推断场景中验证T-MEX，涵盖数值模拟与真实世界生态视频分析，结果表明该框架和评分能有效评估表示的可识别性及其在因果下游任务中的实用性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。