Saved in:
Bibliographic Details
Main Authors: Lu, Cheng, Zeng, Jiusun, Xia, Yu, Cai, Jinhui, Luo, Shihua
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2404.01078
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915594029236224
author Lu, Cheng
Zeng, Jiusun
Xia, Yu
Cai, Jinhui
Luo, Shihua
author_facet Lu, Cheng
Zeng, Jiusun
Xia, Yu
Cai, Jinhui
Luo, Shihua
contents Shapley value is a widely used tool in explainable artificial intelligence (XAI), as it provides a principled way to attribute contributions of input features to model outputs. However, estimation of Shapley value requires capturing conditional dependencies among all feature combinations, which poses significant challenges in complex data environments. In this article, EmSHAP (Energy-based model for Shapley value estimation), an accurate Shapley value estimation method, is proposed to estimate the expectation of Shapley contribution function under the arbitrary subset of features given the rest. By utilizing the ability of energy-based model (EBM) to model complex distributions, EmSHAP provides an effective solution for estimating the required conditional probabilities. To further improve estimation accuracy, a GRU (Gated Recurrent Unit)-coupled partition function estimation method is introduced. The GRU network captures long-term dependencies with a lightweight parameterization and maps input features into a latent space to mitigate the influence of feature ordering. Additionally, a dynamic masking mechanism is incorporated to further enhance the robustness and accuracy by progressively increasing the masking rate. Theoretical analysis on the error bound as well as application to four case studies verified the higher accuracy and better scalability of EmSHAP in contrast to competitive methods.
format Preprint
id arxiv_https___arxiv_org_abs_2404_01078
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Energy-Based Model for Accurate Estimation of Shapley Values in Feature Attribution
Lu, Cheng
Zeng, Jiusun
Xia, Yu
Cai, Jinhui
Luo, Shihua
Machine Learning
Shapley value is a widely used tool in explainable artificial intelligence (XAI), as it provides a principled way to attribute contributions of input features to model outputs. However, estimation of Shapley value requires capturing conditional dependencies among all feature combinations, which poses significant challenges in complex data environments. In this article, EmSHAP (Energy-based model for Shapley value estimation), an accurate Shapley value estimation method, is proposed to estimate the expectation of Shapley contribution function under the arbitrary subset of features given the rest. By utilizing the ability of energy-based model (EBM) to model complex distributions, EmSHAP provides an effective solution for estimating the required conditional probabilities. To further improve estimation accuracy, a GRU (Gated Recurrent Unit)-coupled partition function estimation method is introduced. The GRU network captures long-term dependencies with a lightweight parameterization and maps input features into a latent space to mitigate the influence of feature ordering. Additionally, a dynamic masking mechanism is incorporated to further enhance the robustness and accuracy by progressively increasing the masking rate. Theoretical analysis on the error bound as well as application to four case studies verified the higher accuracy and better scalability of EmSHAP in contrast to competitive methods.
title Energy-Based Model for Accurate Estimation of Shapley Values in Feature Attribution
topic Machine Learning
url https://arxiv.org/abs/2404.01078