paper-with-me

홈 › Papers

Alternative Methods to SHAP Derived from Properties of Kernels: A Note on Theoretical Analysis

2024-06-01 · Kazuhiro Hiraki, Shinichi Ishihara, Junnosuke Shino

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.

📄 PDF Abstract BibTeX arXiv:2406.00371

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

SHAP 설명 없음
LIME LIME, or Local Interpretable Model-Agnostic Explanations, is an algorithm that can explain the predictions of any classifier or regressor in a faithful way, by…

Similar Papers 제목 키워드 기반

A la Carte - Learning Fast Kernels

2014-12-19 · Zichao Yang, Alexander J. Smola, Le Song, Andrew Gordon Wilson

Kernel methods have great promise for learning rich statistical representations of large modern datasets. However, compared to neural networks, kernel methods have been perceived as lacking in scalability and flexibility…

Schoenberg-Rao distances: Entropy-based and geometry-aware statistical Hilbert distances

2020-02-19 · Gaëtan Hadjeres, Frank Nielsen

Distances between probability distributions that take into account the geometry of their sample space,like the Wasserstein or the Maximum Mean Discrepancy (MMD) distances have received a lot of attention in machine learn…

BIG-bench Machine LearningDensity Estimation

KernelSHAP-IQ: Weighted Least-Square Optimization for Shapley Interactions

2024-05-17 · Fabian Fumagalli, Maximilian Muschalik, Patrick Kolpaczki, Eyke Hüllermeier 외

The Shapley value (SV) is a prevalent approach of allocating credit to machine learning (ML) entities to understand black box ML models. Enriching such interpretations with higher-order interactions is inevitable for com…

Literature Review: Graph Kernels in Chemoinformatics

2022-08-09 · James Young

The purpose of this review is to introduce the reader to graph kernels and the corresponding literature, with an emphasis on those with direct application to chemoinformatics. Graph kernels are functions that allow for t…

Drug Design

Novel Convolution Kernels for Computer Vision and Shape Analysis based on Electromagnetism

2018-06-20 · Dominique Beaini, Sofiane Achiche, Yann-Seing Law-Kam Cio, Maxime Raison

Computer vision is a growing field with a lot of new applications in automation and robotics, since it allows the analysis of images and shapes for the generation of numerical or analytical information. One of the most u…