Combination of Weak Learners eXplanations to Improve Random Forest eXplicability Robustness

The notion of robustness in XAI refers to the observed variations in the explanation of the prediction of a learned model with respect to changes in the input leading to that prediction. Intuitively, if the input being explained is modified slightly subtly enough so as to not change the prediction o...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2024-02
Main Authors: Pala, Riccardo, García-Cuesta, Esteban
Format: Article
Language:English
Subjects:
Robustness
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Pala, Riccardo
García-Cuesta, Esteban
description The notion of robustness in XAI refers to the observed variations in the explanation of the prediction of a learned model with respect to changes in the input leading to that prediction. Intuitively, if the input being explained is modified slightly subtly enough so as to not change the prediction of the model too much, then we would expect that the explanation provided for that new input does not change much either. We argue that a combination through discriminative averaging of ensembles weak learners explanations can improve the robustness of explanations in ensemble methods.This approach has been implemented and tested with post-hoc SHAP method and Random Forest ensemble with successful results. The improvements obtained have been measured quantitatively and some insights into the explicability robustness in ensemble methods are presented.
format article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2933659210</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2933659210</sourcerecordid><originalsourceid>FETCH-proquest_journals_29336592103</originalsourceid><addsrcrecordid>eNqNjMEKgkAURYcgSMp_eNBa0Jm0XEtS0EqCghYy1ghjOs_mjUF_n1Qf0Oouzjl3wjwuRBRsVpzPmE_UhGHIkzWPY-GxS4ZdpY10Gg1gDScl73BQ0hplCdS5b-UXEjiEfddbfCoopLlhBzlaRe5j6ausdKvdCwqsBnJGES3YtJYtKf-3c7bMt8dsF4wnj2EsywYHa0ZU8lSIJE55FIr_rDeufUOW</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2933659210</pqid></control><display><type>article</type><title>Combination of Weak Learners eXplanations to Improve Random Forest eXplicability Robustness</title><source>Publicly Available Content Database</source><creator>Pala, Riccardo ; García-Cuesta, Esteban</creator><creatorcontrib>Pala, Riccardo ; García-Cuesta, Esteban</creatorcontrib><description>The notion of robustness in XAI refers to the observed variations in the explanation of the prediction of a learned model with respect to changes in the input leading to that prediction. Intuitively, if the input being explained is modified slightly subtly enough so as to not change the prediction of the model too much, then we would expect that the explanation provided for that new input does not change much either. We argue that a combination through discriminative averaging of ensembles weak learners explanations can improve the robustness of explanations in ensemble methods.This approach has been implemented and tested with post-hoc SHAP method and Random Forest ensemble with successful results. The improvements obtained have been measured quantitatively and some insights into the explicability robustness in ensemble methods are presented.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Robustness</subject><ispartof>arXiv.org, 2024-02</ispartof><rights>2024. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://www.proquest.com/docview/2933659210?pq-origsite=primo$$EHTML$$P50$$Gproquest$$Hfree_for_read</linktohtml><link.rule.ids>780,784,25753,37012,44590</link.rule.ids></links><search><creatorcontrib>Pala, Riccardo</creatorcontrib><creatorcontrib>García-Cuesta, Esteban</creatorcontrib><title>Combination of Weak Learners eXplanations to Improve Random Forest eXplicability Robustness</title><title>arXiv.org</title><description>The notion of robustness in XAI refers to the observed variations in the explanation of the prediction of a learned model with respect to changes in the input leading to that prediction. Intuitively, if the input being explained is modified slightly subtly enough so as to not change the prediction of the model too much, then we would expect that the explanation provided for that new input does not change much either. We argue that a combination through discriminative averaging of ensembles weak learners explanations can improve the robustness of explanations in ensemble methods.This approach has been implemented and tested with post-hoc SHAP method and Random Forest ensemble with successful results. The improvements obtained have been measured quantitatively and some insights into the explicability robustness in ensemble methods are presented.</description><subject>Robustness</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>PIMPY</sourceid><recordid>eNqNjMEKgkAURYcgSMp_eNBa0Jm0XEtS0EqCghYy1ghjOs_mjUF_n1Qf0Oouzjl3wjwuRBRsVpzPmE_UhGHIkzWPY-GxS4ZdpY10Gg1gDScl73BQ0hplCdS5b-UXEjiEfddbfCoopLlhBzlaRe5j6ausdKvdCwqsBnJGES3YtJYtKf-3c7bMt8dsF4wnj2EsywYHa0ZU8lSIJE55FIr_rDeufUOW</recordid><startdate>20240229</startdate><enddate>20240229</enddate><creator>Pala, Riccardo</creator><creator>García-Cuesta, Esteban</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20240229</creationdate><title>Combination of Weak Learners eXplanations to Improve Random Forest eXplicability Robustness</title><author>Pala, Riccardo ; García-Cuesta, Esteban</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_29336592103</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Robustness</topic><toplevel>online_resources</toplevel><creatorcontrib>Pala, Riccardo</creatorcontrib><creatorcontrib>García-Cuesta, Esteban</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni)</collection><collection>ProQuest Central</collection><collection>ProQuest Central Essentials</collection><collection>AUTh Library subscriptions: ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Pala, Riccardo</au><au>García-Cuesta, Esteban</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Combination of Weak Learners eXplanations to Improve Random Forest eXplicability Robustness</atitle><jtitle>arXiv.org</jtitle><date>2024-02-29</date><risdate>2024</risdate><eissn>2331-8422</eissn><abstract>The notion of robustness in XAI refers to the observed variations in the explanation of the prediction of a learned model with respect to changes in the input leading to that prediction. Intuitively, if the input being explained is modified slightly subtly enough so as to not change the prediction of the model too much, then we would expect that the explanation provided for that new input does not change much either. We argue that a combination through discriminative averaging of ensembles weak learners explanations can improve the robustness of explanations in ensemble methods.This approach has been implemented and tested with post-hoc SHAP method and Random Forest ensemble with successful results. The improvements obtained have been measured quantitatively and some insights into the explicability robustness in ensemble methods are presented.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2024-02
issn 2331-8422
language eng
recordid cdi_proquest_journals_2933659210
source Publicly Available Content Database
subjects Robustness
title Combination of Weak Learners eXplanations to Improve Random Forest eXplicability Robustness
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-26T23%3A00%3A10IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Combination%20of%20Weak%20Learners%20eXplanations%20to%20Improve%20Random%20Forest%20eXplicability%20Robustness&rft.jtitle=arXiv.org&rft.au=Pala,%20Riccardo&rft.date=2024-02-29&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2933659210%3C/proquest%3E%3Cgrp_id%3Ecdi_FETCH-proquest_journals_29336592103%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2933659210&rft_id=info:pmid/&rfr_iscdi=true