可解释的联邦学习:工业设置的生命周期仪表板

IF 1.6 4区计算机科学 Q3 COMPUTER SCIENCE, INFORMATION SYSTEMS

IEEE Pervasive Computing Pub Date : 2023-01-01 DOI:10.1109/MPRV.2022.3229166

Michael Ungersböck, Thomas Hiessl, D. Schall, F. Michahelles

{"title":"可解释的联邦学习:工业设置的生命周期仪表板","authors":"Michael Ungersböck, Thomas Hiessl, D. Schall, F. Michahelles","doi":"10.1109/MPRV.2022.3229166","DOIUrl":null,"url":null,"abstract":"As the adoption of federated learning (FL) in the manufacturing industry grows and systems get increasingly complex, a need to inspect their behavior arises. Stakeholders of the FL process want a more transparent system to understand the current state and analyze how its performance changed over time. However, current representation approaches are often not designed for industrial applications and do not cover the entire FL model lifecycle. We propose the lifecycle dashboard, which considers the different requirements and perspectives of industrial stakeholders by visualizing information from the FL server. In addition, our representation approach is generic enough to be applied to different use cases and industries. We evaluate the lifecycle dashboard in a semistructured expert interview, show improvements in the understandability of FL systems, and discuss possible use cases in the industry.","PeriodicalId":55021,"journal":{"name":"IEEE Pervasive Computing","volume":"22 1","pages":"19-28"},"PeriodicalIF":1.6000,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":"{\"title\":\"Explainable Federated Learning: A Lifecycle Dashboard for Industrial Settings\",\"authors\":\"Michael Ungersböck, Thomas Hiessl, D. Schall, F. Michahelles\",\"doi\":\"10.1109/MPRV.2022.3229166\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"As the adoption of federated learning (FL) in the manufacturing industry grows and systems get increasingly complex, a need to inspect their behavior arises. Stakeholders of the FL process want a more transparent system to understand the current state and analyze how its performance changed over time. However, current representation approaches are often not designed for industrial applications and do not cover the entire FL model lifecycle. We propose the lifecycle dashboard, which considers the different requirements and perspectives of industrial stakeholders by visualizing information from the FL server. In addition, our representation approach is generic enough to be applied to different use cases and industries. We evaluate the lifecycle dashboard in a semistructured expert interview, show improvements in the understandability of FL systems, and discuss possible use cases in the industry.\",\"PeriodicalId\":55021,\"journal\":{\"name\":\"IEEE Pervasive Computing\",\"volume\":\"22 1\",\"pages\":\"19-28\"},\"PeriodicalIF\":1.6000,\"publicationDate\":\"2023-01-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"2\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IEEE Pervasive Computing\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://doi.org/10.1109/MPRV.2022.3229166\",\"RegionNum\":4,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"COMPUTER SCIENCE, INFORMATION SYSTEMS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Pervasive Computing","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1109/MPRV.2022.3229166","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"COMPUTER SCIENCE, INFORMATION SYSTEMS","Score":null,"Total":0}

引用次数: 2

摘要

随着联邦学习(FL)在制造业中的应用越来越多，系统变得越来越复杂，需要检查它们的行为。FL过程的利益相关者想要一个更透明的系统来理解当前状态，并分析其性能如何随时间变化。然而，当前的表示方法通常不是为工业应用而设计的，并且没有覆盖整个FL模型生命周期。我们提出了生命周期仪表板，它通过可视化来自FL服务器的信息来考虑工业利益相关者的不同需求和观点。此外，我们的表示方法足够通用，可以应用于不同的用例和行业。我们在半结构化的专家访谈中评估了生命周期仪表板，展示了FL系统可理解性的改进，并讨论了行业中可能的用例。

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

Explainable Federated Learning: A Lifecycle Dashboard for Industrial Settings

As the adoption of federated learning (FL) in the manufacturing industry grows and systems get increasingly complex, a need to inspect their behavior arises. Stakeholders of the FL process want a more transparent system to understand the current state and analyze how its performance changed over time. However, current representation approaches are often not designed for industrial applications and do not cover the entire FL model lifecycle. We propose the lifecycle dashboard, which considers the different requirements and perspectives of industrial stakeholders by visualizing information from the FL server. In addition, our representation approach is generic enough to be applied to different use cases and industries. We evaluate the lifecycle dashboard in a semistructured expert interview, show improvements in the understandability of FL systems, and discuss possible use cases in the industry.

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

IEEE Pervasive Computing 工程技术-电信学

CiteScore

4.10

自引率

0.00%

发文量

审稿时长

>12 weeks

期刊介绍： IEEE Pervasive Computing explores the role of computing in the physical world–as characterized by visions such as the Internet of Things and Ubiquitous Computing. Designed for researchers, practitioners, and educators, this publication acts as a catalyst for realizing the ideas described by Mark Weiser in 1988. The essence of this vision is the creation of environments saturated with sensing, computing, and wireless communication that gracefully support the needs of individuals and society. Many key building blocks for this vision are now viable commercial technologies: wearable and handheld computers, wireless networking, location sensing, Internet of Things platforms, and so on. However, the vision continues to present deep challenges for experts in areas such as hardware design, sensor networks, mobile systems, human-computer interaction, industrial design, machine learning, data science, and societal issues including privacy and ethics. Through special issues, the magazine explores applications in areas such as assisted living, automotive systems, cognitive assistance, hardware innovations, ICT4D, manufacturing, retail, smart cities, and sustainability. In addition, the magazine accepts peer-reviewed papers of wide interest under a general call, and also features regular columns on hot topics and interviews with luminaries in the field.