Assessing Alignment and Stability of Feature Importance Explanations via Weight of Evidence
Mirrored from arXiv — Machine Learning for archival readability. Support the source by reading on the original site.
Computer Science > Machine Learning
Title:Assessing Alignment and Stability of Feature Importance Explanations via Weight of Evidence
Abstract:Feature importance Methods (FIMs) are widely used in Explainable AI to interpret model predictions, yet attribution scores alone often provide limited insight into the underlying reasoning process. In this work, we introduce a novel perspective by embedding FIMs within a hypothesis-testing framework based on Weight of Evidence (WoE). We quantify how strongly the observed evidence supports any given hypothesis on feature importance. The reference hypothesis can stem from domain knowledge, ground truth, or be derived from the FIM itself. This formulation enables a principled evaluation of FIMs, capturing both their alignment with prior knowledge and their variability. We further provide theoretical results linking WoE to attribution variance. Empirical results shows the applicability and flexibility of our strategy analyzing LIME and SHAP explanations in settings with different reference hypotheses. Overall, our framework offers a complementary tool for assessing FIMs through a contrastive, evidence-based lens.
| Comments: | Accepted at XKDD and Beyond 2026 Workshop, ECML-PKDD |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2609.00090 [cs.LG] |
| (or arXiv:2609.00090v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2609.00090
arXiv-issued DOI via DataCite (pending registration)
|
Access Paper:
- View PDF
- HTML (experimental)
- TeX Source
References & Citations
Bookmark
Bibliographic and Citation Tools
Code, Data and Media Associated with this Article
Demos
Recommenders and Search Tools
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
More from arXiv — Machine Learning
-
Equation Recast for Canonical Operator Learning Across Parametric PDEs
Sep 4
-
From Euclidean to Graph-Structured Data: A Survey of Collaborative Learning
Sep 4
-
Modern Transformers Are Implicit Hybrids: From Functional Differentiation to Principled Hybrid Architecture Design
Sep 4
-
Tail-Likelihood Reinforcement Learning
Sep 4
Discussion (0)
Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.
Sign in →No comments yet. Sign in and be the first to say something.