Frugal Machine Learning

TL;DR

This paper explores resource-efficient machine learning methods suitable for wearable devices, focusing on maintaining high accuracy while minimizing computational and energy costs, especially in privacy-sensitive applications.

Contribution

It introduces the concept of frugal learning, evaluates various algorithms under resource constraints, and demonstrates their practical deployment on a smartwatch for activity recognition.

Findings

Certain algorithms achieve high accuracy with minimal resources.

Frugal learning enables on-device model training in privacy-sensitive scenarios.

Real-world smartwatch implementation confirms feasibility and effectiveness.

Abstract

Machine learning, already at the core of increasingly many systems and applications, is set to become even more ubiquitous with the rapid rise of wearable devices and the Internet of Things. In most machine learning applications, the main focus is on the quality of the results achieved (e.g., prediction accuracy), and hence vast amounts of data are being collected, requiring significant computational resources to build models. In many scenarios, however, it is infeasible or impractical to set up large centralized data repositories. In personal health, for instance, privacy issues may inhibit the sharing of detailed personal data. In such cases, machine learning should ideally be performed on wearable devices themselves, which raises major computational limitations such as the battery capacity of smartwatches. This paper thus investigates frugal learning, aimed to build the most accurate possible models using the least amount of resources. A wide range of learning algorithms is examined through a frugal lens, analyzing their accuracy/runtime performance on a wide range of data sets. The most promising algorithms are thereafter assessed in a real-world scenario by implementing them in a smartwatch and letting them learn activity recognition models on the watch itself.