From local explanations to global understanding with explainable AI for trees

计算机科学
作者
Scott Lundberg,Gabriel Erion,Hugh Chen,Alex J. DeGrave,Jordan M. Prutkin,Bala G. Nair,Ronit Katz,Jonathan Himmelfarb,Nisha Bansal,Su‐In Lee
出处
期刊:Nature Machine Intelligence [Nature Portfolio]
卷期号:2 (1): 56-67 被引量:5448
标识
DOI:10.1038/s42256-019-0138-9
摘要

Tree-based machine learning models such as random forests, decision trees and gradient boosted trees are popular nonlinear predictive models, yet comparatively little attention has been paid to explaining their predictions. Here we improve the interpretability of tree-based models through three main contributions. (1) A polynomial time algorithm to compute optimal explanations based on game theory. (2) A new type of explanation that directly measures local feature interaction effects. (3) A new set of tools for understanding global model structure based on combining many local explanations of each prediction. We apply these tools to three medical machine learning problems and show how combining many high-quality local explanations allows us to represent global structure while retaining local faithfulness to the original model. These tools enable us to (1) identify high-magnitude but low-frequency nonlinear mortality risk factors in the US population, (2) highlight distinct population subgroups with shared risk characteristics, (3) identify nonlinear interaction effects among risk factors for chronic kidney disease and (4) monitor a machine learning model deployed in a hospital by identifying which features are degrading the model's performance over time. Given the popularity of tree-based machine learning models, these improvements to their interpretability have implications across a broad set of domains. Tree-based machine learning models are widely used in domains such as healthcare, finance and public services. The authors present an explanation method for trees that enables the computation of optimal local explanations for individual predictions, and demonstrate their method on three medical datasets.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
量子星尘发布了新的文献求助10
刚刚
如如要动完成签到,获得积分10
1秒前
卡卡西应助星宇采纳,获得50
2秒前
贪玩飞机发布了新的文献求助10
2秒前
太阳完成签到,获得积分10
2秒前
脑洞疼应助Li采纳,获得10
3秒前
hutian完成签到,获得积分10
3秒前
3秒前
4秒前
默默荔枝完成签到 ,获得积分10
4秒前
SYLH应助打工人采纳,获得10
4秒前
王w完成签到,获得积分10
4秒前
SYLH应助wen采纳,获得10
5秒前
bkagyin应助夏梦园采纳,获得10
5秒前
如如要动发布了新的文献求助200
5秒前
6秒前
FFFFFFG完成签到,获得积分10
7秒前
7秒前
8秒前
9秒前
sigla发布了新的文献求助10
9秒前
wss完成签到,获得积分10
9秒前
跳跃忆灵完成签到,获得积分10
9秒前
左凝阳发布了新的文献求助10
9秒前
风中幻梦发布了新的文献求助10
10秒前
10秒前
10秒前
SYLH应助飞云采纳,获得10
10秒前
研友_VZG7GZ应助疗效采纳,获得10
11秒前
11秒前
11秒前
一朵梅花完成签到,获得积分10
13秒前
14秒前
monoklatt发布了新的文献求助30
14秒前
wss发布了新的文献求助10
15秒前
脑洞疼应助大剑日太刀采纳,获得10
15秒前
Synan完成签到,获得积分10
16秒前
李健的小迷弟应助orange9采纳,获得10
16秒前
tx完成签到,获得积分20
17秒前
艾小晗发布了新的文献求助20
17秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
Cognitive Neuroscience: The Biology of the Mind 1000
Technical Brochure TB 814: LPIT applications in HV gas insulated switchgear 1000
Toward a Combinatorial Approach for the Prediction of IgG Half-Life and Clearance 500
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Picture Books with Same-sex Parented Families: Unintentional Censorship 500
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3970120
求助须知:如何正确求助?哪些是违规求助? 3514810
关于积分的说明 11176124
捐赠科研通 3250136
什么是DOI,文献DOI怎么找? 1795198
邀请新用户注册赠送积分活动 875647
科研通“疑难数据库(出版商)”最低求助积分说明 804964