Aumann-SHAP: 机器学习中反事实交互解释的几何结构
Aumann-SHAP: The Geometry of Counterfactual Interaction Explanations in Machine Learning
AI总结：
提出Aumann-SHAP框架，通过局部超立方体网格分解反事实转移，利用微博弈Shapley和LES值实现几何感知归因，在合成数据上纠正了等分Shapley的偏差，在真实数据上修正了符号错误并提高了编辑效率。
摘要：
我们引入Aumann-SHAP，一个交互感知框架，通过将模型限制在连接基线和反事实特征的局部超立方体来分解反事实转移。每个超立方体被离散化为一个网格，以构建一个诱导的微玩家合作博弈，其中基本网格步移动成为玩家。该TU-微博弈上的Shapley和LES值产生几何感知的域内归因，在网格细化下收敛到对角Aumann-Shapley / Integrated Gradients极限，并将等分Shapley恢复为退化的$m=1$特例。精确的网格状态闭式公式为固定交互阶数提供了多项式时间计算。在具有已知真实值的合成基准上，等分Shapley带有不可约偏差，而Aumann-SHAP收敛到正确分解。在German Credit上，交互几何在$12.3\%$的实例中改变了特征优先级排序。在UCI Heart Disease上，等分错误地将胆固醇抑制因子归因为正贡献者，这是Aumann-SHAP纠正的符号错误。在MNIST上，博弈论归因达到目标置信度所需的编辑次数比基于幅度的排序少$3.5\ imes$，其中微博弈Shapley在所有预算下实现了最佳效率。
英文摘要：
We introduce Aumann-SHAP, an interaction-aware framework that decomposes counterfactual transitions by restricting the model to a local hypercube connecting baseline and counterfactual features. Each hypercube is discretized into a grid to construct an induced micro-player cooperative game in which elementary grid-step moves become players. Shapley and LES values on this TU-micro-game yield geometry-aware within-pot attributions that converge to the diagonal Aumann--Shapley / Integrated Gradients limit under grid refinement, and recover equal-split Shapley as the degenerate $m=1$ special case. An exact grid-state closed form gives polynomial-time computation for fixed interaction order. On a synthetic benchmark with known ground truth, equal-split Shapley carries an irreducible bias while Aumann-SHAP converges to the correct decomposition. On German Credit, interaction geometry changes feature priority rankings in $12.3\%$ of instances. On UCI Heart Disease, equal-split misattributes a cholesterol suppressor as a positive contributor, which is a sign error Aumann-SHAP corrects. On MNIST, game-theoretic attribution reaches target confidence with $3.5\times$ fewer edits than magnitude-based ordering, with micro-game Shapley achieving the best efficiency across all budgets.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
