# BayaHAR: Lightweight Bayesian Few-Shot User Adaptation for On-Device Personalized Human Activity Recognition

arXiv: https://arxiv.org/abs/2606.04798 · HTML: https://mlsanity.com/paper/2606.04798/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 36 references that are in the map.
- First posted on arXiv 3 Jun 2026.

## Builds on (most cited first, 19 of 19)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Deep CORAL: Correlation Alignment for Deep Domain Adaptation](https://mlsanity.com/paper/1607.01719/) (2016)
- [Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2002.08546/) (2020)
- [Efficient Test-Time Model Adaptation without Forgetting](https://mlsanity.com/paper/2204.02610/) (2022)
- [On Episodes, Prototypical Networks, and Few-shot Learning](https://mlsanity.com/paper/2012.09831/) (2020)
- [Tiny Machine Learning: Progress and Futures](https://mlsanity.com/paper/2403.19076/) (2024)
- [WEAR: An Outdoor Sports Dataset for Wearable and Egocentric Activity Recognition](https://mlsanity.com/paper/2304.05088/) (2023)
- [TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devices](https://mlsanity.com/paper/2507.07949/) (2025)
- [NEO: No-Optimization Test-Time Adaptation through Latent Re-Centering](https://mlsanity.com/paper/2510.05635/) (2025)
- [Lifelong Adaptive Machine Learning for Sensor-based Human Activity Recognition Using Prototypical Networks](https://mlsanity.com/paper/2203.05692/) (2022)
- [Foundation Models Defining A New Era In Sensor-based Human Activity Recognition: A Survey And Outlook](https://mlsanity.com/paper/2604.02711/) (2026)
- [Learning Class-level Prototypes for Few-shot Learning](https://mlsanity.com/paper/2108.11072/) (2021)
- [Feed-Forward Source-Free Domain Adaptation via Class Prototypes](https://mlsanity.com/paper/2307.10787/) (2023)
- [CODA: A Continuous Online Evolve Framework for Deploying HAR Sensing Systems](https://mlsanity.com/paper/2403.14922/) (2024)
- [WHAR Datasets: An Open Source Library for Wearable Human Activity Recognition](https://mlsanity.com/paper/2508.16604/) (2025)
- [Reducing Label Dependency in Human Activity Recognition with Wearables: From Supervised Learning to Novel Weakly Self-Supervised Approaches](https://mlsanity.com/paper/2512.19713/) (2025)

## Abstract (arXiv)

Sensor-based Human Activity Recognition (HAR) models often degrade on unseen users due to domain shifts caused by individual movement patterns and sensor placement. Practical wearable HAR systems therefore require personalization methods that are lightweight, applicable across diverse calibration scenarios, and robust under limited calibration data. We present BayaHAR, a gradient-free framework that repurposes pretrained HAR classifiers as Prototypical Networks using prior prototypes that preserve zero-shot performance while regularizing adaptation. For labeled calibration data, we introduce closed-form Bayesian prototype estimation and extend the same principle to weakly labeled data, requiring only knowledge of which activities were performed. With only 3 seconds of calibration (one shot) per activity, supervised adaptation improves test macro-F1 on unseen users by +2.76 to +33.44 percentage points across four datasets, while weakly supervised adaptation improves by +0.56 to +32.13 points. Since adaptation requires only closed-form prototype updates, the framework enables efficient and robust on-device personalization of preexisting HAR classifiers.