保持智能:从智能产品到可持续智能产品

2023 IEEE/ACM 7th International Workshop on Green And Sustainable Software (GREENS) Pub Date : 2023-05-01 DOI:10.1109/GREENS59328.2023.00013

Samdyuti Suri, S. Das, Kuntal Dey, Kapil Singi, V. Sharma, Vikrant S. Kaulgud

{"title":"保持智能:从智能产品到可持续智能产品","authors":"Samdyuti Suri, S. Das, Kuntal Dey, Kapil Singi, V. Sharma, Vikrant S. Kaulgud","doi":"10.1109/GREENS59328.2023.00013","DOIUrl":null,"url":null,"abstract":"Retraining is an essential process for the sustainability of any production Machine Learning (ML) model and/or any software with ML based components, as retraining addresses the problem of data shift. However, uncertainty from different sources makes the successful retraining a challenging task. Here, we provide an outline of a multi-armed bandit based decision framework, which can address the uncertainty related to a retraining framework of any production ML model.","PeriodicalId":438486,"journal":{"name":"2023 IEEE/ACM 7th International Workshop on Green And Sustainable Software (GREENS)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Sustain the Smartness: From Smart Things to Sustainable Smart Things\",\"authors\":\"Samdyuti Suri, S. Das, Kuntal Dey, Kapil Singi, V. Sharma, Vikrant S. Kaulgud\",\"doi\":\"10.1109/GREENS59328.2023.00013\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Retraining is an essential process for the sustainability of any production Machine Learning (ML) model and/or any software with ML based components, as retraining addresses the problem of data shift. However, uncertainty from different sources makes the successful retraining a challenging task. Here, we provide an outline of a multi-armed bandit based decision framework, which can address the uncertainty related to a retraining framework of any production ML model.\",\"PeriodicalId\":438486,\"journal\":{\"name\":\"2023 IEEE/ACM 7th International Workshop on Green And Sustainable Software (GREENS)\",\"volume\":\"23 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-05-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2023 IEEE/ACM 7th International Workshop on Green And Sustainable Software (GREENS)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/GREENS59328.2023.00013\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2023 IEEE/ACM 7th International Workshop on Green And Sustainable Software (GREENS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/GREENS59328.2023.00013","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 0

摘要

再培训是任何生产机器学习(ML)模型和/或任何基于ML组件的软件的可持续性的重要过程，因为再培训解决了数据转移问题。然而，来自不同来源的不确定性使得成功的再培训成为一项具有挑战性的任务。在这里，我们提供了一个基于多臂强盗的决策框架的大纲，它可以解决与任何生产ML模型的再训练框架相关的不确定性。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Sustain the Smartness: From Smart Things to Sustainable Smart Things

Retraining is an essential process for the sustainability of any production Machine Learning (ML) model and/or any software with ML based components, as retraining addresses the problem of data shift. However, uncertainty from different sources makes the successful retraining a challenging task. Here, we provide an outline of a multi-armed bandit based decision framework, which can address the uncertainty related to a retraining framework of any production ML model.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

2023 IEEE/ACM 7th International Workshop on Green And Sustainable Software (GREENS)

自引率

0.00%

发文量