Abstract:Feature attributions often hide a critical modeling choice: they explain a prediction along a counterfactual path from a reference state to an input. Different baselines, interpolations, and generative trajectories define different paths and can therefor produce different explanations. We study this path ambiguity as a modeling problem. Our central question is whether the path can be chosen by the data-generating transport process, rather than by a hand-designed interpolation or by the sensitivity geometry of the model being explained. We separate attribution into fixed-path credit allocation and path selection. For a fixed path, we prove that the Aumann-Shapley line integral is the unique attribution rule under standard fixed-path axioms and explicit coordinate-trace regularity. For path selection, we minimize kinetic action over flows that transport a reference distribution to the data distribution, yielding a transport-geodesic attribution principle. We approximate this ideal with Rectified Flow and Reflow and derive stability bounds linking vector-field error to attribution error. Experiments show that lower-action, transport-consistent paths produce more stable and structured explanations, preserving competitive deletion faithfulness, without claiming data-manifold membership. Our code is available at this https URL.
| Comments: | 10 figures, 31 pages |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV) |
| Cite as: | arXiv:2603.05093 [cs.LG] |
| (or arXiv:2603.05093v2 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2603.05093 arXiv-issued DOI via DataCite |
Submission history
From: Cenwei Zhang [view email]
[v1]
Thu, 5 Mar 2026 12:05:20 UTC (4,061 KB)
[v2]
Wed, 13 May 2026 15:28:32 UTC (3,722 KB)