# When Adaptation Hurts: Split Sensitivity and Person-Level Negative Transfer in Federated Wearable Onboarding

arXiv: https://arxiv.org/abs/2609.27819 · HTML: https://mlsanity.com/paper/2609.27819/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 29 references that are in the map.
- First posted on arXiv 18 Aug 2026.

## Builds on (most cited first, 17 of 17)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Federated Optimization in Heterogeneous Networks](https://mlsanity.com/paper/1812.06127/) (2018)
- [Ditto: Fair and Robust Federated Learning Through Personalization](https://mlsanity.com/paper/2012.04221/) (2020)
- [FedBN: Federated Learning on Non-IID Features via Local Batch Normalization](https://mlsanity.com/paper/2102.07623/) (2021)
- [Federated Learning with Personalization Layers](https://mlsanity.com/paper/1912.00818/) (2019)
- [Continual Test-Time Domain Adaptation](https://mlsanity.com/paper/2203.13591/) (2022)
- [Efficient Test-Time Model Adaptation without Forgetting](https://mlsanity.com/paper/2204.02610/) (2022)
- [Towards Stable Test-Time Adaptation in Dynamic Wild World](https://mlsanity.com/paper/2302.12400/) (2023)
- [FedHealth: A Federated Transfer Learning Framework for Wearable Healthcare](https://mlsanity.com/paper/1907.09173/) (2019)
- [On Pitfalls of Test-Time Adaptation](https://mlsanity.com/paper/2306.03536/) (2023)
- [UniMiB SHAR: a new dataset for human activity recognition using acceleration data from smartphones](https://mlsanity.com/paper/1611.07688/) (2016)
- [Adaptive Test-Time Personalization for Federated Learning](https://mlsanity.com/paper/2310.18816/) (2023)
- [Optimization-Free Test-Time Adaptation for Cross-Person Activity Recognition](https://mlsanity.com/paper/2310.18562/) (2023)
- [Beyond the Federation: Topology-aware Federated Learning for Generalization to Unseen Clients](https://mlsanity.com/paper/2407.04949/) (2024)
- [BoTTA: Benchmarking on-device Test Time Adaptation](https://mlsanity.com/paper/2504.10149/) (2025)
- [PI-TTA: Physics-Informed Source-Free Test-Time Adaptation for Robust Human Activity Recognition on Mobile Devices](https://mlsanity.com/paper/2604.25435/) (2026)
- [Temporal Structure Matters for Efficient Test-Time Adaptation in Wearable Human Activity Recognition](https://mlsanity.com/paper/2605.04617/) (2026)

## Abstract (arXiv)

Federated wearable models eventually serve people absent from source training, but favorable average accuracy does not establish that unlabeled onboarding helps each person. We evaluate six core onboarding strategies on five wearable datasets under a leakage-controlled protocol that fixes source checkpoints, estimates normalization from source data only, separates calibration from evaluation recordings, and performs inference over held-out people rather than windows, devices, or random seeds. Completing all eligible HHAR and PAMAP2 outer-person rotations materially changes the conclusion obtained from the original frozen fold. On HHAR, balanced accuracy on that single person is 95.6-97.2% across methods versus 78.3-83.0% over all nine users, a reduction of 13.8-17.8 percentage points (pp). The displayed mean leader changes on both datasets, while paired leader-runner bootstrap intervals include zero and do not resolve a superior method. No adaptive core mechanism combines positive mean gain in all five datasets with zero seed-averaged person-level losses greater than 2 percentage points (pp). FedBN has one such loss and ATP-style adaptation has eight; Feature-only has none after seed averaging, but its exact one-sided 95% upper bound is 7.6%. A complementary seed-person stress audit records 4, 22, and 10 harmful realizations out of 114 for FedBN, ATP-style, and Feature-only, respectively; these are repeated realizations, not independent participants. Tail quality, calibration availability, and fall-window specificity reveal additional failures hidden by mean accuracy. The study therefore provides an auditable development benchmark and failure map rather than a universal-superiority or deployment-safety claim.