# Domain Generalization for Smartphone-Based Human Activity Recognition: A Systematic Analysis of Components and Interactions

arXiv: https://arxiv.org/abs/2609.14863 · HTML: https://mlsanity.com/paper/2609.14863/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 50 references that are in the map.
- First posted on arXiv 14 Sep 2026.

## Builds on (most cited first, 27 of 27)

- [Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization](https://mlsanity.com/paper/1911.08731/) (2019)
- [Deep CORAL: Correlation Alignment for Deep Domain Adaptation](https://mlsanity.com/paper/1607.01719/) (2016)
- [In Search of Lost Domain Generalization](https://mlsanity.com/paper/2007.01434/) (2020)
- [Generalizing to Unseen Domains: A Survey on Domain Generalization](https://mlsanity.com/paper/2103.03097/) (2021)
- [Out-of-Distribution Generalization via Risk Extrapolation (REx)](https://mlsanity.com/paper/2003.00688/) (2020)
- [Domain Generalization with MixStyle](https://mlsanity.com/paper/2104.02008/) (2021)
- [TS2Vec: Towards Universal Representation of Time Series](https://mlsanity.com/paper/2106.10466/) (2021)
- [Self-Challenging Improves Cross-Domain Generalization](https://mlsanity.com/paper/2007.02454/) (2020)
- [Gradient Matching for Domain Generalization](https://mlsanity.com/paper/2104.09937/) (2021)
- [Self-Supervised Contrastive Pre-Training For Time Series via Time-Frequency Consistency](https://mlsanity.com/paper/2206.08496/) (2022)
- [Fishr: Invariant Gradient Variances for Out-of-Distribution Generalization](https://mlsanity.com/paper/2109.02934/) (2021)
- [Exact Feature Distribution Matching for Arbitrary Style Transfer and Domain Generalization](https://mlsanity.com/paper/2203.07740/) (2022)
- [Mobile Sensor Data Anonymization](https://mlsanity.com/paper/1810.11546/) (2018)
- [Recognizing Detailed Human Context In-the-Wild from Smartphones and Smartwatches](https://mlsanity.com/paper/1609.06354/) (2016)
- [Domain-invariant Feature Exploration for Domain Generalization](https://mlsanity.com/paper/2207.12020/) (2022)
- [Semantic-Discriminative Mixup for Generalizable Sensor-based Cross-domain Activity Recognition](https://mlsanity.com/paper/2206.06629/) (2022)
- [Domain Generalization in Computational Pathology: Survey and Guidelines](https://mlsanity.com/paper/2310.19656/) (2023)
- [Domain generalization of 3D semantic segmentation in autonomous driving](https://mlsanity.com/paper/2212.04245/) (2022)
- [ERM++: An Improved Baseline for Domain Generalization](https://mlsanity.com/paper/2304.01973/) (2023)
- [Self-supervised Representation Learning From Random Data Projectors](https://mlsanity.com/paper/2310.07756/) (2023)
- [Domain Generalisation via Risk Distribution Matching](https://mlsanity.com/paper/2310.18598/) (2023)
- [Dynamic Domain Generalization](https://mlsanity.com/paper/2205.13913/) (2022)
- [Is Large-Scale Pretraining the Secret to Good Domain Generalization?](https://mlsanity.com/paper/2412.02856/) (2024)
- [FIXED: Frustratingly Easy Domain Generalization with Mixup](https://mlsanity.com/paper/2211.05228/) (2022)
- [Towards Generalizable Human Activity Recognition: A Survey](https://mlsanity.com/paper/2508.12213/) (2025)
- [HAROOD: A Benchmark for Out-of-distribution Generalization in Sensor-based Human Activity Recognition](https://mlsanity.com/paper/2512.10807/) (2025)
- [Why Domain Generalization Fail? A View of Necessity and Sufficiency](https://mlsanity.com/paper/2502.10716/) (2025)

## Abstract (arXiv)

Smartphone-based Human Activity Recognition (HAR) models often degrade under distribution shifts caused by changes in users, devices, sensor placements, environments, and acquisition protocols. Domain Generalization (DG) addresses this problem by learning from source domains without access to target data. Existing DG methods span training objectives, representation initialization, and architectural modifications, but these components are typically evaluated in isolation despite operating at different stages of the learning pipeline. We present a large-scale controlled benchmark of DG for smartphone-based HAR, comprising more than 410,000 experiments across four model architectures, thirteen training objectives including Empirical Risk Minimization (ERM), five initialization strategies, four architectural configurations, and two shift scenarios: cross-dataset and cross-position. Results show that individual DG components provide limited and highly conditional gains. Alternative objectives rarely outperform ERM consistently, self-supervised initialization helps in specific settings, and architectural modifications, particularly Dynamic Domain Generalization, provide the clearest standalone improvements. Joint configurations, however, frequently outperform their individual components and exhibit complementary and sometimes super-additive interactions, although gains remain model- and shift-dependent. Class-level analysis shows that the strongest configurations mainly improve difficult, shift-sensitive decision boundaries. Finally, oracle checkpoint analysis reveals substantial unrealized performance: source-validation selection recovers only 53% and 26% of the available oracle gain in cross-dataset and cross-position settings, respectively. Overall, effective HAR domain generalization requires jointly designing DG components and robust model-selection strategies.