Print Email Facebook Twitter Tiny, Always-on, and Fragile Title Tiny, Always-on, and Fragile: Bias Propagation through Design Choices in On-device Machine Learning Workflows Author Hutiri, Wiebke (TU Delft Information and Communication Technology) Ding, Aaron Yi (TU Delft Information and Communication Technology) Kawsar, Fahim (Nokia Bell Labs) Mathur, Akhil (Nokia Bell Labs) Date 2023 Abstract Billions of distributed, heterogeneous, and resource constrained IoT devices deploy on-device machine learning (ML) for private, fast, and offline inference on personal data. On-device ML is highly context dependent and sensitive to user, usage, hardware, and environment attributes. This sensitivity and the propensity toward bias in ML makes it important to study bias in on-device settings. Our study is one of the first investigations of bias in this emerging domain and lays important foundations for building fairer on-device ML. We apply a software engineering lens, investigating the propagation of bias through design choices in on-device ML workflows. We first identify reliability bias as a source of unfairness and propose a measure to quantify it. We then conduct empirical experiments for a keyword spotting task to show how complex and interacting technical design choices amplify and propagate reliability bias. Our results validate that design choices made during model training, like the sample rate and input feature type, and choices made to optimize models, like light-weight architectures, the pruning learning rate, and pruning sparsity, can result in disparate predictive performance across male and female groups. Based on our findings, we suggest low effort strategies for engineers to mitigate bias in on-device ML. Subject audio keyword spottingBiasdesign choicesembedded machine learningfairnesson-device machine learningpersonal data To reference this document use: http://resolver.tudelft.nl/uuid:37763437-5a91-4eea-b1c0-3ffb87f7fc99 DOI https://doi.org/10.1145/3591867 ISSN 1049-331X Source ACM Transactions on Software Engineering and Methodology, 32 (6) Part of collection Institutional Repository Document type journal article Rights © 2023 Wiebke Hutiri, Aaron Yi Ding, Fahim Kawsar, Akhil Mathur Files PDF 3591867.pdf 5.58 MB Close viewer /islandora/object/uuid:37763437-5a91-4eea-b1c0-3ffb87f7fc99/datastream/OBJ/view