Scholarlink

<p>Interpreting machine learning models fairly and efficiently remains challenging, particularly when features are correlated. Classical Shapley-based explanations can split attribution among substitutes and are often computationally demanding. This study presents <i>iAdditive</i>, a model-agnostic approach that promotes fairness by grouping highly correlated or redundant features through group-level attribution semantics and improves efficiency via a dynamic coalition heuristic inspired by additive explanation methods. Experiments on simulated datasets with known structure and on NHANES indicate that iAdditive produces faithful global attributions under correlation while achieving substantial runtime reductions compared with KernelSHAP, TreeSHAP, SAGE, and exact Shapley baselines. By balancing fairness, interpretability, and efficiency, iAdditive provides a practical tool for trustworthy decision support in applications such as health care.</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

iAdditive: fast and fair Shapley-inspired feature attribution for correlated features

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年7月22日

查看全文
  • Abirami Gunasekaran,
  • Minsi Chen,
  • Richard Hill,
  • Keith McCabe

摘要

Interpreting machine learning models fairly and efficiently remains challenging, particularly when features are correlated. Classical Shapley-based explanations can split attribution among substitutes and are often computationally demanding. This study presents iAdditive, a model-agnostic approach that promotes fairness by grouping highly correlated or redundant features through group-level attribution semantics and improves efficiency via a dynamic coalition heuristic inspired by additive explanation methods. Experiments on simulated datasets with known structure and on NHANES indicate that iAdditive produces faithful global attributions under correlation while achieving substantial runtime reductions compared with KernelSHAP, TreeSHAP, SAGE, and exact Shapley baselines. By balancing fairness, interpretability, and efficiency, iAdditive provides a practical tool for trustworthy decision support in applications such as health care.