Matches in SemOpenAlex for { <https://semopenalex.org/work/W4384111993> ?p ?o ?g. }
Showing items 1 to 55 of
55
with 100 items per page.
- W4384111993 abstract "This thesis explores open-sourced machine learning (ML) model explanation tools to understand whether these tools can allow a layman to visualize, understand, and suggest intuitive remedies to unfairness in ML-based decision-support systems. Machine learning models trained on datasets biased against minority groups are increasingly used to guide life-altering social decisions, prompting the urgent need to study their logic for unfairness. Due to this problem's impact on vast populations of the general public, it is critical for the layperson -- not just subject matter experts in social justice or machine learning experts -- to understand the nature of unfairness within these algorithms and the potential trade-offs. Existing research on fairness in machine learning focuses mostly on the mathematical definitions and tools to understand and remedy unfair models, with some directly citing user-interactive tools as necessary for future work. This thesis presents FairLay-ML, a proof-of-concept GUI integrating some of the most promising tools to provide intuitive explanations for unfair logic in ML models by integrating existing research tools (e.g. Local Interpretable Model-Agnostic Explanations) with existing ML-focused GUI (e.g. Python Streamlit). We test FairLay-ML using models of various accuracy and fairness generated by an unfairness detector tool, Parfait-ML, and validate our results using Themis. Our study finds that the technology stack used for FairLay-ML makes it easy to install and provides real-time black-box explanations of pre-trained models to users. Furthermore, the explanations provided translate to actionable remedies." @default.
- W4384111993 created "2023-07-13" @default.
- W4384111993 creator A5010830558 @default.
- W4384111993 creator A5039824925 @default.
- W4384111993 creator A5076300752 @default.
- W4384111993 date "2023-07-11" @default.
- W4384111993 modified "2023-10-16" @default.
- W4384111993 title "FairLay-ML: Intuitive Remedies for Unfairness in Data-Driven Social-Critical Algorithms" @default.
- W4384111993 doi "https://doi.org/10.48550/arxiv.2307.05029" @default.
- W4384111993 hasPublicationYear "2023" @default.
- W4384111993 type Work @default.
- W4384111993 citedByCount "0" @default.
- W4384111993 crossrefType "posted-content" @default.
- W4384111993 hasAuthorship W4384111993A5010830558 @default.
- W4384111993 hasAuthorship W4384111993A5039824925 @default.
- W4384111993 hasAuthorship W4384111993A5076300752 @default.
- W4384111993 hasBestOaLocation W43841119931 @default.
- W4384111993 hasConcept C107457646 @default.
- W4384111993 hasConcept C11413529 @default.
- W4384111993 hasConcept C119857082 @default.
- W4384111993 hasConcept C154945302 @default.
- W4384111993 hasConcept C17744445 @default.
- W4384111993 hasConcept C199360897 @default.
- W4384111993 hasConcept C199539241 @default.
- W4384111993 hasConcept C2522767166 @default.
- W4384111993 hasConcept C41008148 @default.
- W4384111993 hasConcept C519991488 @default.
- W4384111993 hasConcept C67597806 @default.
- W4384111993 hasConceptScore W4384111993C107457646 @default.
- W4384111993 hasConceptScore W4384111993C11413529 @default.
- W4384111993 hasConceptScore W4384111993C119857082 @default.
- W4384111993 hasConceptScore W4384111993C154945302 @default.
- W4384111993 hasConceptScore W4384111993C17744445 @default.
- W4384111993 hasConceptScore W4384111993C199360897 @default.
- W4384111993 hasConceptScore W4384111993C199539241 @default.
- W4384111993 hasConceptScore W4384111993C2522767166 @default.
- W4384111993 hasConceptScore W4384111993C41008148 @default.
- W4384111993 hasConceptScore W4384111993C519991488 @default.
- W4384111993 hasConceptScore W4384111993C67597806 @default.
- W4384111993 hasLocation W43841119931 @default.
- W4384111993 hasOpenAccess W4384111993 @default.
- W4384111993 hasPrimaryLocation W43841119931 @default.
- W4384111993 hasRelatedWork W2090215046 @default.
- W4384111993 hasRelatedWork W2529681551 @default.
- W4384111993 hasRelatedWork W2891993883 @default.
- W4384111993 hasRelatedWork W2979801952 @default.
- W4384111993 hasRelatedWork W3148954008 @default.
- W4384111993 hasRelatedWork W4225307033 @default.
- W4384111993 hasRelatedWork W4285225238 @default.
- W4384111993 hasRelatedWork W4285815787 @default.
- W4384111993 hasRelatedWork W4312949351 @default.
- W4384111993 hasRelatedWork W77035938 @default.
- W4384111993 isParatext "false" @default.
- W4384111993 isRetracted "false" @default.
- W4384111993 workType "article" @default.