Tiny, always-on and fragile: Bias propagation through design choices in on-device machine learning workflows

by   Wiebke Toussaint, et al.
Delft University of Technology

Billions of distributed, heterogeneous and resource constrained smart consumer devices deploy on-device machine learning (ML) to deliver private, fast and offline inference on personal data. On-device ML systems are highly context dependent, and sensitive to user, usage, hardware and environmental attributes. Despite this sensitivity and the propensity towards bias in ML, bias in on-device ML has not been studied. This paper studies the propagation of bias through design choices in on-device ML development workflows. We position reliablity bias, which arises from disparate device failures across demographic groups, as a source of unfairness in on-device ML settings and quantify metrics to evaluate it. We then identify complex and interacting technical design choices in the on-device ML workflow that can lead to disparate performance across user groups, and thus reliability bias. Finally, we show with an empirical case study that seemingly innocuous design choices such as the data sample rate, pre-processing parameters used to construct input features and pruning hyperparameters propagate reliability bias through an audio keyword spotting development workflow. We leverage our insights to suggest strategies for developers to develop fairer on-device ML.


page 1

page 2

page 3

page 4


GPU-based Private Information Retrieval for On-Device Machine Learning Inference

On-device machine learning (ML) inference can enable the use of private ...

Learning by Design: Structuring and Documenting the Human Choices in Machine Learning Development

The influence of machine learning (ML) is quickly spreading, and a numbe...

Distilling On-Device Intelligence at the Network Edge

Devices at the edge of wireless networks are the last mile data sources ...

On-device Training: A First Overview on Existing Systems

The recent breakthroughs in machine learning (ML) and deep learning (DL)...

Pick the Right Edge Device: Towards Power and Performance Estimation of CUDA-based CNNs on GPGPUs

The emergence of Machine Learning (ML) as a powerful technique has been ...

Please sign up or login with your details

Forgot password? Click here to reset