Self-adapting Machine Learning-based Systems via a Probabilistic Model Checking Framework

Author:

Casimiro Maria1ORCID,Soares Diogo2ORCID,Garlan David2ORCID,Rodrigues Luís3ORCID,Romano Paolo3ORCID

Affiliation:

1. S3D, Carnegie Mellon University, Pittsburgh, USA and IST, Universidade de Lisboa, Lisbon, Portugal

2. S3D, Carnegie Mellon University, Pittsburgh, USA

3. INESC-ID, IST, Universidade de Lisboa, Lisboa, Portugal

Abstract

This article focuses on the problem of optimizing the system utility of Machine Learning (ML)-based systems in the presence of ML mispredictions. This is achieved via the use of self-adaptive systems and through the execution of adaptation tactics, such as model retraining , which operate at the level of individual ML components. To address this problem, we propose a probabilistic modeling framework that reasons about the cost/benefit tradeoffs associated with adapting ML components. The key idea of the proposed approach is to decouple the problems of estimating (1) the expected performance improvement after adaptation and (2) the impact of ML adaptation on overall system utility. We apply the proposed framework to engineer a self-adaptive ML-based fraud detection system, which we evaluate using a publicly available, real fraud detection dataset. We initially consider a scenario in which information on the model’s quality is immediately available. Next, we relax this assumption by integrating (and extending) state-of-the-art techniques for estimating the model’s quality in the proposed framework. We show that by predicting the system utility stemming from retraining an ML component, the probabilistic model checker can generate adaptation strategies that are significantly closer to the optimal, as compared against baselines such as periodic or reactive retraining.

Publisher

Association for Computing Machinery (ACM)

Reference69 articles.

1. IEEE Computational Intelligence Society. 2019. IEEE-CIS Fraud Detection. IEEE Computational Intelligence Society. https://www.kaggle.com/competitions/ieee-fraud-detection/overview

2. Chris Deotte. 2019. IEEE-CIS Fraud Detection Winner Solution. Nvidia. https://www.kaggle.com/code/cdeotte/xgb-fraud-with-magic-0-9600

3. ARMS: Automated rules management system for fraud detection;Aparício David;arXiv preprint arXiv:2002.06075,2020

4. Christopher Bishop and Nasser Nasrabadi. 2006. Pattern Recognition and Machine Learning. Vol. 4. Springer.

5. Tomáš Bureš. 2021. Self-adaptation 2.0. In 2021 International Symposium on Software Engineering for Adaptive and Self-Managing Systems (SEAMS’21). IEEE 262–263.

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3