研究人员开发了一种名为OddSHAP的新方法来估计Shapley值，这是机器学习归因的关键工具。这种新颖的方法侧重于集合函数的“奇数分量”，该分量已被确定为Shapley值的唯一决定因素。通过一种称为配对采样（paired sampling）的技术过滤掉无关的“偶数分量”，OddSHAP实现了最先进的准确性，尤其是在较大的采样预算下。 AI
影响 引入了一种更准确的模型可解释性和特征归因方法。
排序理由 该集群包含一篇学术论文，详细介绍了机器学习中估计Shapley值的新方法。[lever_c_demoted from research: ic=1 ai=1.0]
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2606.02247v1 Announce Type: new Abstract: Shapley values are a principled attribution measure widely used in interpretable machine learning, but their exact computation scales exponentially with the number of players, motivating a wide range of approximation methods based o…
arXiv:2602.01399v2 Announce Type: replace-cross Abstract: The Shapley value is a ubiquitous framework for attribution in machine learning, encompassing feature importance, data valuation, and causal inference. However, its exact computation is generally intractable, necessitating…