发表机构
Università degli Studi di Bari Aldo Moro; rAIse s.r.l.（巴里阿尔多·莫罗大学; rAIse有限公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出预测-解释不变性问题，通过比较Frobenius和trace几何在神经影像数据上的应用，发现数据几何虽保持预测性能，但改变局部解释结构，揭示了几何作为可解释性隐藏自由度的作用。
AI 中文摘要
在科学领域中，经验数据常常产生正半定矩阵，这些矩阵编码相似性、耦合或相互作用，并诱导出自然几何。我们研究改变用于比较相同经验表示的几何是否保持受试者层面的性能和解释所依据的局部结构，这一问题我们称为预测-解释不变性问题。我们通过比较应用于相同经验矩阵的Frobenius和trace几何，在形态学MRI、fMRI和EEG数据上解决这一问题。预测性能在几何间大致保持，但可比的性能并不意味受试者层面决策分数或预测标签的一致性。预测相似性也掩盖了几何依赖的局部邻域、扰动敏感性和解释排序的差异。降维使两个受试者空间几何逐渐一致，而分类性能和决策层面的一致性下降。这些结果将数据几何识别为可解释性中的一个隐藏自由度：相似的性能并不保证不变的决策或解释。
英文摘要
Across scientific domains, empirical data often give rise to positive semidefinite matrices that encode similarities, couplings or interactions and induce natural geometries. We investigate whether changing the geometry used to compare the same empirical representations preserves subject-level performance and the local structures from which explanations are derived, a question we term the prediction explanation invariance problem. We address this problem across morphometric MRI, fMRI and EEG data by comparing Frobenius and trace geometries applied to the same empirical matrices. Predictive performance was broadly preserved across geometries, but comparable performance did not imply agreement in subject-level decision scores or predicted labels. Predictive similarity also masked geometry-dependent differences in local neighbourhoods, perturbation sensitivities and explanatory rankings. Dimensionality reduction made the two subject-space geometries progressively more concordant, while classification performance and decision-level agreement declined. These results identify data geometry as a hidden degree of freedom in explainability: similar performance does not guarantee invariant decisions or explanations.
