Saved in:
Bibliographic Details
Main Authors: Hiraki, Kazuhiro, Ishihara, Shinichi, Shino, Junnosuke
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2406.00371
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929428453392384
author Hiraki, Kazuhiro
Ishihara, Shinichi
Shino, Junnosuke
author_facet Hiraki, Kazuhiro
Ishihara, Shinichi
Shino, Junnosuke
contents This study first derives a general and analytical expression of AFA (Additive Feature Attribution) in terms of the kernel in LIME (Local Interpretable Model-agnostic Explanations). Then, we propose some new AFAs that have appropriate properties of kernels or that coincide with the LS prenucleolus in cooperative game theory. We also revisit existing AFAs such as SHAP (SHapley Additive exPlanations) and re-examine the properties of their kernels.
format Preprint
id arxiv_https___arxiv_org_abs_2406_00371
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Alternative Methods to SHAP Derived from Properties of Kernels: A Note on Theoretical Analysis
Hiraki, Kazuhiro
Ishihara, Shinichi
Shino, Junnosuke
Machine Learning
This study first derives a general and analytical expression of AFA (Additive Feature Attribution) in terms of the kernel in LIME (Local Interpretable Model-agnostic Explanations). Then, we propose some new AFAs that have appropriate properties of kernels or that coincide with the LS prenucleolus in cooperative game theory. We also revisit existing AFAs such as SHAP (SHapley Additive exPlanations) and re-examine the properties of their kernels.
title Alternative Methods to SHAP Derived from Properties of Kernels: A Note on Theoretical Analysis
topic Machine Learning
url https://arxiv.org/abs/2406.00371