提出无需依赖特定目标的因果解释方法，让复杂场景下的可解释性更实用。
Practical do-Shapley Explanations with Estimand-Agnostic Causal Inference
- 用不依赖具体目标的因果推断方法，统一处理各类可识别查询
- 单个模型即可估计任意可识别问题，计算速度显著提升
- 适用于无法直接访问数据生成过程的场景，适合实际应用
在可解释性技术中，SHAP虽流行但常忽略因果结构。do-SHAP采用干预查询，但受限于具体目标（estimand），难以实用。本文提出估计算量无关的方法，仅需一个模型即可估计任意可识别查询，使do-SHAP在复杂图结构上可行。同时开发新算法大幅加速计算，代价极低，并提出解释不可访问数据生成过程的方法。在两个真实数据集上验证了其估计精度与计算效率，展示了获得可靠解释的巨大潜力。
原文摘要 · Abstract (English)
Among explainability techniques, SHAP stands out as one of the most popular, but often overlooks the causal structure of the problem. In response, do-SHAP employs interventional queries, but its reliance on estimands hinders its practical application. To address this problem, we propose the use of estimand-agnostic approaches, which allow for the estimation of any identifiable query from a single model, making do-SHAP feasible on complex graphs. We also develop a novel algorithm to significantly accelerate its computation at a negligible cost, as well as a method to explain inaccessible Data Generating Processes. We demonstrate the estimation and computational performance of our approach, and validate it on two real-world datasets, highlighting its potential in obtaining reliable explanations.
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。