Please use this identifier to cite or link to this item:
http://hdl.handle.net/1893/36287
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Adair, Jason | en_UK |
dc.contributor.author | Thomson, Sarah L | en_UK |
dc.contributor.author | Brownlee, Alexander E I | en_UK |
dc.date.accessioned | 2024-10-08T00:02:58Z | - |
dc.date.available | 2024-10-08T00:02:58Z | - |
dc.date.issued | 2024-08-01 | en_UK |
dc.identifier.uri | http://hdl.handle.net/1893/36287 | - |
dc.description.abstract | We analyse tness landscapes of evolutionary feature selection to obtain information about feature importance in supervised machine learning. Local optima networks (LONs) are a compact representation of a landscape, and can potentially be adapted for use in explainable artiicial intelligence (XAI). This work examines their applicability for discerning feature importance in supervised machine learning datasets. We visualise aspects of feature selection LONs for a breast cancer prediction dataset as case study, and this process reveals information about the composition of feature sets for the underlying ML models. The estimations of feature importance obtained from LONs are compared with the coeecients extracted from logistic regression models (interpretable AI), and also against feature importances obtained through an established XAI technique: SHAP (explainable AI). We nd that the features present in the LON are not strongly correlated with the model coeecients and SHAP values derived from a model trained prior to feature selection, nor are they strongly correlated within similar groups of local optima after feature selection, calling into question the eeects of constraining the feature space for wrapper-based techniques based on such ranking metrics. | en_UK |
dc.language.iso | en | en_UK |
dc.publisher | ACMDL | en_UK |
dc.relation | Adair J, Thomson SL & Brownlee AEI (2024) Explaining evolutionary feature selection via local optima networks. In: GECCO '24 Companion: Genetic and Evolutionary Computation Conference Companion, Melbourne, Australia, 14.07.2024-18.05.2024. ACMDL. https://doi.org/10.1145/3638530.3664183 | en_UK |
dc.rights | This work is licensed under a Creative Commons Attribution International 4.0 License. GECCO ’24 Companion, July 14–18, 2024, Melbourne, VIC, Australia © 2024 Copyright held by the owner/author(s) | en_UK |
dc.rights.uri | http://creativecommons.org/licenses/by/4.0/ | en_UK |
dc.subject | CCS CONCEPTS | en_UK |
dc.subject | Mathematics of computing | en_UK |
dc.subject | Graph algorithms | en_UK |
dc.subject | Combina- torial algorithms | en_UK |
dc.subject | Theory of computation → Evolutionary algorithms KEYWORDS Fitness Landscapes | en_UK |
dc.subject | Explainable AI | en_UK |
dc.subject | Local Optima Networks (LONs) | en_UK |
dc.title | Explaining evolutionary feature selection via local optima networks | en_UK |
dc.type | Conference Paper | en_UK |
dc.identifier.doi | 10.1145/3638530.3664183 | en_UK |
dc.citation.publicationstatus | Published | en_UK |
dc.type.status | VoR - Version of Record | en_UK |
dc.author.email | alexander.brownlee@stir.ac.uk | en_UK |
dc.citation.conferencedates | 2024-07-14 - 2024-05-18 | en_UK |
dc.citation.conferencelocation | Melbourne, Australia | en_UK |
dc.citation.conferencename | GECCO '24 Companion: Genetic and Evolutionary Computation Conference Companion | en_UK |
dc.citation.date | 01/08/2024 | en_UK |
dc.contributor.affiliation | Computing Science | en_UK |
dc.contributor.affiliation | Edinburgh Napier University | en_UK |
dc.contributor.affiliation | Computing Science and Mathematics - Division | en_UK |
dc.identifier.scopusid | 2-s2.0-85201973695 | en_UK |
dc.identifier.wtid | 2009526 | en_UK |
dc.contributor.orcid | 0000-0003-2892-5059 | en_UK |
dc.date.accepted | 2024-05-03 | en_UK |
dcterms.dateAccepted | 2024-05-03 | en_UK |
dc.date.filedepositdate | 2024-09-03 | en_UK |
rioxxterms.apc | paid | en_UK |
rioxxterms.type | Conference Paper/Proceeding/Abstract | en_UK |
rioxxterms.version | VoR | en_UK |
local.rioxx.author | Adair, Jason| | en_UK |
local.rioxx.author | Thomson, Sarah L| | en_UK |
local.rioxx.author | Brownlee, Alexander E I|0000-0003-2892-5059 | en_UK |
local.rioxx.project | Internal Project|University of Stirling|https://isni.org/isni/0000000122484331 | en_UK |
local.rioxx.freetoreaddate | 2024-10-07 | en_UK |
local.rioxx.licence | http://creativecommons.org/licenses/by/4.0/|2024-10-07| | en_UK |
local.rioxx.filename | wksp216s2-file1.pdf | en_UK |
local.rioxx.filecount | 1 | en_UK |
Appears in Collections: | Computing Science and Mathematics Conference Papers and Proceedings |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
wksp216s2-file1.pdf | Fulltext - Published Version | 1.91 MB | Adobe PDF | View/Open |
This item is protected by original copyright |
A file in this item is licensed under a Creative Commons License
Items in the Repository are protected by copyright, with all rights reserved, unless otherwise indicated.
The metadata of the records in the Repository are available under the CC0 public domain dedication: No Rights Reserved https://creativecommons.org/publicdomain/zero/1.0/
If you believe that any material held in STORRE infringes copyright, please contact library@stir.ac.uk providing details and we will remove the Work from public display in STORRE and investigate your claim.