Detecting trade-offs between fairness, stability, and accuracy for responsible machine learning model selection

理论(学习稳定性) 选择(遗传算法) 机器学习 计算机科学 人工智能
作者
Denys Herasymuk,Andrii Poliakov,Volodymyr Fedorchenko
出处
期刊:Sučasnij stan naukovih doslìdženʹ ta tehnologìj v promislovostì [Kharkiv National University of Radioelectronics]
卷期号: (1(31)): 5-19
标识
DOI:10.30837/2522-9818.2025.1.005
摘要

The subject of the study in the article is the process of machine learning model selection performed by data scientists to build models in critical areas. The purpose of the work: 1) create a software library for measuring the accuracy, stability, and fairness of models; 2) conduct experiments to identify trade-offs between fairness, stability, and accuracy; 3) propose a responsible model selection process to improve the safety of using machine learning models. The article provides for the following tasks: to measure the fairness and stability of machine learning models and to investigate their relationship with the accuracy of models. The following methods are introduced: empirical evaluation, the theory of decomposition of model error into bias and variance, the theory of algorithmic fairness, and methods for quantitative assessment of uncertainty. Results achieved: 1) low predictive variability is proposed as a desirable property to ensure safety and equality of variability between different social groups as a new metric of fairness of machine learning models; 2) it is demonstrated how stability analysis helps specialists overcome the challenges of model multiplicity and choose reliable, stable and fair models; 3) an open-source software framework for community use is created that integrates stability measurements into model development processes. Conclusions. This work proposes a new paradigm of group fairness that combines the issues of correctness/quality and randomness/stability from the research agenda of responsible artificial intelligence. The application of the proposed approaches helps in the responsible selection of machine learning models under conditions of model multiplicity, demonstrating that, although there may be many models with comparable accuracy, there is only one (or a few) "best" model that is reliable, fair and stable, as it should be.

科研通智能强力驱动
Strongly Powered by AbleSci AI
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
科研通AI6.2的应助被tjl采纳,获得10
刚刚
邱燈完成签到,获得积分10
1秒前
SciGPT的应助被外向的大狮子采纳,获得10
2秒前
2秒前
天天快乐的应助被6666采纳,获得10
2秒前
伶俐绿柏完成签到,获得积分10
3秒前
3秒前
传奇3的应助被JF123_采纳,获得10
3秒前
Owen的应助被yansiyi采纳,获得20
4秒前
eerrtt完成签到,获得积分10
5秒前
5秒前
5秒前
松下完成签到,获得积分10
5秒前
6秒前
打打的应助被廖翰彬采纳,获得10
6秒前
6秒前
Qiiiyoung完成签到,获得积分10
6秒前
张远幸发布了新的文献求助10
7秒前
7秒前
7秒前
peng完成签到,获得积分10
7秒前
8秒前
缺粥发布了新的文献求助10
9秒前
华仔的应助被吴呜呜采纳,获得10
10秒前
所所的应助被1111采纳,获得10
10秒前
Micheallee完成签到,获得积分10
10秒前
Hello的应助被老汉憨憨采纳,获得10
11秒前
科研通AI6.4的应助被dde采纳,获得30
11秒前
12秒前
个性天晴完成签到 ,获得积分10
13秒前
13秒前
鲤鱼鑫磊发布了新的文献求助10
13秒前
丘比特的应助被zyy采纳,获得30
13秒前
111发布了新的文献求助10
13秒前
14秒前
科研通AI65的应助被西北采纳,获得10
14秒前
14秒前
14秒前
搞怪冷之完成签到 ,获得积分10
14秒前
14秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
八旗制度の研究 600
高分子基功能界面水蒸发材料与应用研究 500
外场增强的水汽发电研究 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8187362
求助须知:如何正确求助?哪些是违规求助? 9575478
关于积分的说明 21841431
捐赠科研通 7785067
什么是DOI,文献DOI怎么找? 3434943
关于科研通互助平台的介绍 2559401
邀请新用户注册赠送积分活动 2481820