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 Inte- grated 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 Kullback–Leibler (KL) and Euclidean trust regions; attributions are obtained by integrating input gradients along this trajectory. We further derive FRInGe-B, a target-vs-rest specialization whose rank- one pullback removes the model-dependent Fisher products of full FRInGe. Across six ImageNet architectures, FRInGe most clearly improves Magnitude Aligned Scoring (MAS), while remaining competitive on perturbation area-under-the-curve (AUC) metrics and infidelity.

Top