TL;DR
This paper introduces h-Shap, a scalable, hierarchical Shapley-based explanation method for image classification that improves computational efficiency and accuracy over existing approaches, especially in complex models and specific data distributions.
Contribution
The paper proposes a novel hierarchical extension of Shapley coefficients, enabling scalable and exact explanations without approximation under certain conditions.
Findings
h-Shap outperforms existing methods in accuracy.
h-Shap is significantly faster in computation.
It provides exact explanations under specific assumptions.
Abstract
As modern complex neural networks keep breaking records and solving harder problems, their predictions also become less and less intelligible. The current lack of interpretability often undermines the deployment of accurate machine learning tools in sensitive settings. In this work, we present a model-agnostic explanation method for image classification based on a hierarchical extension of Shapley coefficients--Hierarchical Shap (h-Shap)--that resolves some of the limitations of current approaches. Unlike other Shapley-based explanation methods, h-Shap is scalable and can be computed without the need of approximation. Under certain distributional assumptions, such as those common in multiple instance learning, h-Shap retrieves the exact Shapley coefficients with an exponential improvement in computational complexity. We compare our hierarchical approach with popular Shapley-based and…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
MethodsShapley Additive Explanations
