English(EN) Semiparametric Inference for Conditional Shapley Feature Importance

新方法增强条件Shapley特征重要性推断

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-14 04:00

研究人员开发了一种新的条件Shapley特征重要性推断方法，解决了现有估计量通常只提供点估计量且未能考虑特征依赖性的局限性。所提出的方法在特征的真实条件分布下对“联盟外”特征进行积分，旨在获得一个基于损失的全局重要性度量。该方法在理论上被证明是$\sqrt{n}$-一致且渐近正态的，实证研究表明其置信区间覆盖率和I类错误控制准确。 AI

影响通过改进特征归因方法来增强机器学习模型的可解释性。

排序理由该条目是一篇详细介绍新统计方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv stat.ML 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 20 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该条目是一篇详细介绍新统计方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, other; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv stat.ML TIER_1 English(EN) · Agostino Gnasso · 2026-09-14 04:00

Conditional Shapley Feature Importance 的半参数推断

arXiv:2609.10313v1 Announce Type: cross Abstract: Shapley values are widely used for post-hoc feature attribution, but most estimators return point quantities and do not quantify uncertainty, and popular implementations sample out-of-coalition features from their marginal distrib…

本文如何被排名

报道来源 [1]

Conditional Shapley Feature Importance 的半参数推断

相关实体

相关话题