FedFitTech: A Baseline in Federated Learning for Fitness Tracking

2025-06-20

AI Summary

To address core challenges in FitTech-oriented federated learning (FL)—including label scarcity, data imbalance, user behavioral heterogeneity, and the personalization-generalization trade-off—this paper introduces the first open-source FL benchmark framework tailored for privacy-sensitive activity recognition on wearable devices. Methodologically, we implement a lightweight CNN-LSTM temporal model atop Flower and propose a client-adaptive early-stopping mechanism alongside a distributed imbalance mitigation strategy. Our key contributions are: (1) establishing a FitTech-specific FL evaluation paradigm to advance standardization; (2) achieving a 13% reduction in communication overhead with only a 1% marginal drop in accuracy; and (3) integrating the framework into Flower’s core repository, enabling seamless reproducibility and extensibility for both academic research and industrial deployment.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Computer Vision: Bias, Fairness & Privacy
• Search and Optimization: Distributed Search

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Responsible Web: Data and user privacy-enhancing technologies for the Web
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Rapid evolution of sensors and resource-efficient machine learning models have spurred the widespread adoption of wearable fitness tracking devices. Equipped with inertial sensors, such devices can continuously capture physical movements for fitness technology (FitTech), enabling applications from sports optimization to preventive healthcare. Traditional centralized learning approaches to detect fitness activities struggle with privacy concerns, regulatory constraints, and communication inefficiencies. In contrast, Federated Learning (FL) enables a decentralized model training by communicating model updates rather than private wearable sensor data. Applying FL to FitTech presents unique challenges, such as data imbalance, lack of labelled data, heterogeneous user activity patterns, and trade-offs between personalization and generalization. To simplify research on FitTech in FL, we present the FedFitTech baseline, under the Flower framework, which is publicly available and widely used by both industry and academic researchers. Additionally, to illustrate its usage, this paper presents a case study that implements a system based on the FedFitTech baseline, incorporating a client-side early stopping strategy and comparing the results. For instance, this system allows wearable devices to optimize the trade-off between capturing common fitness activity patterns and preserving individuals'nuances, thereby enhancing both the scalability and efficiency of privacy-aware fitness tracking applications. Results show that this reduces overall redundant communications by 13 percent, while maintaining the overall recognition performance at a negligible recognition cost by 1 percent. Thus, FedFitTech baseline creates a foundation for a wide range of new research and development opportunities in FitTech, and it is available as open-source at: https://github.com/adap/flower/tree/main/baselines/fedfittech

Problem

• Address privacy and efficiency in fitness tracking with Federated Learning
• Overcome data imbalance and heterogeneity in wearable sensor data
• Balance personalization and generalization in activity recognition models

Innovation

• Federated Learning for decentralized fitness tracking
• Client-side early stopping strategy optimization
• Open-source FedFitTech baseline under Flower framework