# FedSCS-XGB -- Federated Server-centric surrogate XGBoost for continual health monitoring

arXiv: https://arxiv.org/abs/2603.06224 · HTML: https://mlsanity.com/paper/2603.06224/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 30 references that are in the map.
- First posted on arXiv 6 Mar 2026.

## Builds on (most cited first, 11 of 11)

- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Flower: A Friendly Federated Learning Research Framework](https://mlsanity.com/paper/2007.14390/) (2020)
- [Split learning for health: Distributed deep learning without sharing raw patient data](https://mlsanity.com/paper/1812.00564/) (2018)
- [FedHealth: A Federated Transfer Learning Framework for Wearable Healthcare](https://mlsanity.com/paper/1907.09173/) (2019)
- [Meta-HAR: Federated Representation Learning for Human Activity Recognition](https://mlsanity.com/paper/2106.00615/) (2021)
- [Gradient-less Federated Gradient Boosting Trees with Learnable Learning Rates](https://mlsanity.com/paper/2304.07537/) (2023)
- [Adaptive Histogram-Based Gradient Boosted Trees for Federated Learning](https://mlsanity.com/paper/2012.06670/) (2020)
- [DDSketch: A fast and fully-mergeable quantile sketch with relative-error guarantees](https://mlsanity.com/paper/1908.10693/) (2019)
- [Federated XGBoost on Sample-Wise Non-IID Data](https://mlsanity.com/paper/2209.01340/) (2022)
- [Towards Adaptive Asynchronous Federated Learning for Human Activity Recognition](https://mlsanity.com/paper/2411.14070/) (2024)
- [Histogram-Based Federated XGBoost using Minimal Variance Sampling for Federated Tabular Data](https://mlsanity.com/paper/2405.02067/) (2024)

## Abstract (arXiv)

Wearable sensors with local data processing can detect health threats early, enhance documentation, and support personalized therapy. In the context of spinal cord injury (SCI), which involves risks such as pressure injuries and blood pressure instability, continuous monitoring can help mitigate these by enabling early deDtection and intervention. In this work, we present a novel distributed machine learning (DML) protocol for human activity recognition (HAR) from wearable sensor data based on gradient-boosted decision trees (XGBoost). The proposed architecture is inspired by Party-Adaptive XGBoost (PAX) while explicitly preserving key structural and optimization properties of standard XGBoost, including histogram-based split construction and tree-ensemble dynamics. First, we provide a theoretical analysis showing that, under appropriate data conditions and suitable hyperparameter selection, the proposed distributed protocol can converge to solutions equivalent to centralized XGBoost training. Second, the protocol is empirically evaluated on a representative wearable-sensor HAR dataset, reflecting the heterogeneity and data fragmentation typical of remote monitoring scenarios. Benchmarking against centralized XGBoost and IBM PAX demonstrates that the theoretical convergence properties are reflected in practice. The results indicate that the proposed approach can match centralized performance up to a gap under 1% while retaining the structural advantages of XGBoost in distributed wearable-based HAR settings.