ScholarMate
English简体中文繁體中文
客服热线:400-1616-289
登录注册
期刊论文

A review and benchmark of feature importance methods for neural networks

Mandler, Hannes*; Weigand, Bernhard
ACM Computing Surveys2024-12DOI: 10.1145/3679012
13阅读
引用收藏
分享

摘要

Feature attribution methods (AMs) are a simple means to provide explanations for the predictions of black- box models such as neural networks. Due to their conceptual differences, the numerous different methods, however, yield ambiguous explanations. While this allows for obtaining different insights into the model, it also complicates the decision regarding which method to adopt. This article summarizes the current state of the art regarding AMs, which includes the requirements and desiderata of the methods themselves as well as the properties of their explanations. Based on a survey of existing methods, a representative subset consisting of the delta-sensitivity index, permutation feature importance, variance-based feature importance in artificial neural networks and DeepSHAP, is described in greater detail and, for the first time, benchmarked in a regression context. Specifically for this purpose, a new verification strategy for model-specific AMs is proposed. As expected, the explanations' agreement with the intuition and among each other clearly depends on the AMs' properties. This has two implications. First, careful reasoning about the selection of an AM is required. Second, it is recommended to apply multiple AMs and combine their insights in order to reduce the model's opacity even further. CCS Concepts: center dot Computing methodologies- Causal reasoning and diagnostics; Neural networks; center dot Information systems- Decision support systems;

学科与关键词

关键词
explainable artificial intelligence (XAI)interpretable machine learningattribution methodfeature importancesensitivity analysis (SA)neural network
相关
加载中…
  • AcME-Accelerated model-agnostic explanations: Fast whitening of the machine-learning black box
    Dandolo, David; Masiero, Chiara; Carletti, Mattia; Pezze, Davide Dalle; Susto, Gian Antonio*EXPERT SYSTEMS WITH APPLICATIONS, 2023, 214: 119115.被引 11
  • To trust or not to trust an explanation: using LEAF to evaluate local linear XAI methods
    Amparore, Elvio*; Perotti, Alan; Bajardi, PaoloPeerJ Computer Science, 2021, e479.被引 40
  • Differentiated Explanation of Deep Neural Networks With Skewed Distributions
    Fu, Weijie; Wang, Meng*; Du, Mengnan; Liu, Ninghao; Hao, Shijie; Hu, XiaIEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, 44(6): 2909-2922.被引 1
查看全部 →

发表信息

论文状态
公开发表
期刊
ACM Computing Surveys
发表日期
2024-12
卷期
第 56 卷, 第 12 期
页码
318
DOI
10.1145/3679012
语言
ENGLISH
成果收录
SCIE
资助标注
MTU Aero Engines AG; Cluster of Excellence SimTech [390740016]

作者

  • M

    Mandler, Hannes (通讯) (第一作者)

  • W

    Weigand, Bernhard

登录解锁更多功能

  • 收藏这篇,随时在“我的 · 收藏”找回
  • 认领你的成果,生成推广素材
  • 关注作者获取最新成果
  • 加入项目组、协同写作
注册 / 登录

产品服务

  • 科研之友
  • 创新城
  • 科创云

服务支持

  • 帮助中心
  • 隐私政策
  • 服务条款

联系方式

在线客服:【】
客服热线:400-1616-289
电子邮箱:support@scholarmate.com

关注或下载科研之友

微信二维码
微信公众号
客户端下载二维码
下载客户端
科研成果科研人员科研机构科研动态爱瑞思软件

©2026 深圳市科研之友网络服务有限公司

公安备案图标粤公网安备 44030502000213
粤ICP备 16046710 号粤B2-20110417