Scholarlink

<p>The Shapley value constitutes a widely recognized tool to assess individual contributions of cooperating entities from a game-theoretic perspective. Within the field of machine learning it is frequently applied to conduct feature attribution or data valuation. Aiming to overcome its deficiencies in capturing intricate interplay between entities, the Shapley interaction index represents a natural extension of the Shapley value, maintaining axiomatic uniqueness. As their complexity renders the exact computation of both quantities impractical, recent work transfers approximation approaches from the Shapley value to Shapley interactions. We propose <i>Permutation-IQ</i>, a domain-independent approximation method based on a novel representation that traces Shapley interactions back to the Shapley value’s fine-grained building blocks of marginal contributions. Sampling these instead of the coarser discrete derivatives of which Shapley interactions are composed, allows to utilize the collected information&#xa0;more&#xa0;efficiently.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Approximating Shapley Interactions with Marginal Contributions

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年5月19日

查看全文
  • Patrick Kolpaczki,
  • Felix Edelmann,
  • Maximilian Muschalik,
  • Eyke Hüllermeier

摘要

The Shapley value constitutes a widely recognized tool to assess individual contributions of cooperating entities from a game-theoretic perspective. Within the field of machine learning it is frequently applied to conduct feature attribution or data valuation. Aiming to overcome its deficiencies in capturing intricate interplay between entities, the Shapley interaction index represents a natural extension of the Shapley value, maintaining axiomatic uniqueness. As their complexity renders the exact computation of both quantities impractical, recent work transfers approximation approaches from the Shapley value to Shapley interactions. We propose Permutation-IQ, a domain-independent approximation method based on a novel representation that traces Shapley interactions back to the Shapley value’s fine-grained building blocks of marginal contributions. Sampling these instead of the coarser discrete derivatives of which Shapley interactions are composed, allows to utilize the collected information more efficiently.