提出新方法提升模型解释的可靠性与校准性。
FRInGe: Distribution-Space Integrated Gradients with Fisher--Rao Geometry
- 在预测分布空间定义参考点与插值路径，避免输入基线依赖
- 在六种ImageNet模型上显著提升MAS评分，校准性更强
- 适合关注模型解释可信度的研究者与开发者
基于梯度的归因方法具有模型忠实性和可扩展性，但集成梯度（IG）易受启发式基线、直线路径、离散化及饱和效应影响。本文提出费舍尔-罗几何集成梯度（FRInGe），将参考点与插值过程均定义在预测分布空间中。FRInGe以最大熵预测参考替代输入基线，并沿概率单纯形上的费舍尔-罗测地线进行插值。对应的输入空间轨迹通过拉回费舍尔度量实现，且由KL与欧氏信任区域稳定。归因结果通过沿该轨迹积分输入梯度获得。在六种ImageNet架构上，FRInGe在以校准为导向的归因指标上表现最优，尤其显著提升MAS分数，同时在扰动AUC与非保真度方面保持竞争力。
原文摘要 · Abstract (English)
Gradient-based attribution methods are model-faithful and scalable, but Integrated Gradients (IG) can be brittle because explanations depend on heuristic baselines, straight-line paths, discretization, and saturation. We propose Fisher--Rao Integrated Gradients (FRInGe), which defines both the reference and interpolation schedule in predictive distribution space. FRInGe replaces input baselines with a maximum-entropy predictive reference and follows a Fisher-Rao geodesic on the probability simplex. The corresponding input-space trajectory is realized through the pullback Fisher metric and stabilized by KL and Euclidean trust regions; attributions are obtained by integrating input gradients along this trajectory. Across six ImageNet architectures, FRInGe most clearly improves calibration-oriented attribution metrics, especially MAS scores, while remaining competitive on perturbation AUC and infidelity.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。