# MergeSFL: Split Federated Learning with Feature Merging and Batch Size Regulation

arXiv: https://arxiv.org/abs/2311.13348 · HTML: https://mlsanity.com/paper/2311.13348/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 83 references that are in the map.
- First posted on arXiv 22 Nov 2023.

## Builds on (most cited first, 30 of 34)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Advances and Open Problems in Federated Learning](https://mlsanity.com/paper/1912.04977/) (2019)
- [Federated Learning with Non-IID Data](https://mlsanity.com/paper/1806.00582/) (2018)
- [Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification](https://mlsanity.com/paper/1909.06335/) (2019)
- [Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition](https://mlsanity.com/paper/1804.03209/) (2018)
- [Deep Double Descent: Where Bigger Models and More Data Hurt](https://mlsanity.com/paper/1912.02292/) (2019)
- [Federated Learning for Mobile Keyboard Prediction](https://mlsanity.com/paper/1811.03604/) (2018)
- [Adaptive Federated Learning in Resource Constrained Edge Computing Systems](https://mlsanity.com/paper/1804.05271/) (2018)
- [Federated Learning in Mobile Edge Networks: A Comprehensive Survey](https://mlsanity.com/paper/1909.11875/) (2019)
- [Split learning for health: Distributed deep learning without sharing raw patient data](https://mlsanity.com/paper/1812.00564/) (2018)
- [Bayesian Nonparametric Federated Learning of Neural Networks](https://mlsanity.com/paper/1905.12022/) (2019)
- [SplitFed: When Federated Learning Meets Split Learning](https://mlsanity.com/paper/2004.12088/) (2020)
- [Applied Federated Learning: Improving Google Keyboard Query Suggestions](https://mlsanity.com/paper/1812.02903/) (2018)
- [FetchSGD: Communication-Efficient Federated Learning with Sketching](https://mlsanity.com/paper/2007.07682/) (2020)
- [Deep Learning with Label Differential Privacy](https://mlsanity.com/paper/2102.06062/) (2021)
- [Federated Learning for Keyword Spotting](https://mlsanity.com/paper/1810.05512/) (2018)
- [Divergence-aware Federated Self-Supervised Learning](https://mlsanity.com/paper/2204.04385/) (2022)
- [Tackling System and Statistical Heterogeneity for Federated Learning with Adaptive Client Sampling](https://mlsanity.com/paper/2112.11256/) (2021)
- [Communication-Efficient and Distributed Learning Over Wireless Networks: Principles and Applications](https://mlsanity.com/paper/2008.02608/) (2020)
- [Revisiting Weighted Aggregation in Federated Learning with Neural Networks](https://mlsanity.com/paper/2302.10911/) (2023)
- [FederatedScope: A Flexible Federated Learning Platform for Heterogeneity](https://mlsanity.com/paper/2204.05011/) (2022)
- [FedBalancer: Data and Pace Control for Efficient Federated Learning on Heterogeneous Clients](https://mlsanity.com/paper/2201.01601/) (2022)
- [Advancements of federated learning towards privacy preservation: from federated learning to split learning](https://mlsanity.com/paper/2011.14818/) (2020)
- [Data Heterogeneity-Robust Federated Learning via Group Client Selection in Industrial IoT](https://mlsanity.com/paper/2202.01512/) (2022)
- [FedSL: Federated Split Learning on Distributed Sequential Data in Recurrent Neural Networks](https://mlsanity.com/paper/2011.03180/) (2020)
- [Server-Side Local Gradient Averaging and Learning Rate Acceleration for Scalable Split Learning](https://mlsanity.com/paper/2112.05929/) (2021)
- [LegoDNN: Block-grained Scaling of Deep Neural Networks for Mobile Vision](https://mlsanity.com/paper/2112.09852/) (2021)

## Built on by (most cited first, 13 of 13)

- [HASFL: Heterogeneity-aware Split Federated Learning over Edge Computing Systems](https://mlsanity.com/paper/2506.08426/) (2025)
- [The Impact of Cut Layer Selection in Split Federated Learning](https://mlsanity.com/paper/2412.15536/) (2024)
- [Adaptive Parameter-Efficient Federated Fine-Tuning on Heterogeneous Devices](https://mlsanity.com/paper/2412.20004/) (2024)
- [Fair Concurrent Training of Multiple Models in Federated Learning](https://mlsanity.com/paper/2404.13841/) (2024)
- [SCALA: Split Federated Learning with Concatenated Activations and Logit Adjustments](https://mlsanity.com/paper/2405.04875/) (2024)
- [Data Heterogeneity and Forgotten Labels in Split Federated Learning](https://mlsanity.com/paper/2511.09736/) (2025)
- [Traversal Learning: A Lossless And Efficient Distributed Learning Framework](https://mlsanity.com/paper/2504.07471/) (2025)
- [Collaborative Batch Size Optimization for Federated Learning](https://mlsanity.com/paper/2506.20511/) (2025)
- [SMoFi: Step-wise Momentum Fusion for Split Federated Learning on Heterogeneous Data](https://mlsanity.com/paper/2511.09828/) (2025)
- [Accelerating Wireless Distributed Learning via Hybrid Split and Federated Learning Optimization](https://mlsanity.com/paper/2511.19851/) (2025)
- [Makespan Minimization in Split Learning: From Theory to Practice](https://mlsanity.com/paper/2602.06693/) (2026)
- [BESplit: Bias-Compensated Split Federated Learning with Evidential Aggregation](https://mlsanity.com/paper/2605.17508/) (2026)
- [When Is Shallow Enough? Adaptive Split Federated Learning with Client-Specific Sufficiency Estimation](https://mlsanity.com/paper/2608.15639/) (2026)

## Abstract (arXiv)

Recently, federated learning (FL) has emerged as a popular technique for edge AI to mine valuable knowledge in edge computing (EC) systems. To mitigate the computing/communication burden on resource-constrained workers and protect model privacy, split federated learning (SFL) has been released by integrating both data and model parallelism. Despite resource limitations, SFL still faces two other critical challenges in EC, i.e., statistical heterogeneity and system heterogeneity. To address these challenges, we propose a novel SFL framework, termed MergeSFL, by incorporating feature merging and batch size regulation in SFL. Concretely, feature merging aims to merge the features from workers into a mixed feature sequence, which is approximately equivalent to the features derived from IID data and is employed to promote model accuracy. While batch size regulation aims to assign diverse and suitable batch sizes for heterogeneous workers to improve training efficiency. Moreover, MergeSFL explores to jointly optimize these two strategies upon their coupled relationship to better enhance the performance of SFL. Extensive experiments are conducted on a physical platform with 80 NVIDIA Jetson edge devices, and the experimental results show that MergeSFL can improve the final model accuracy by 5.82% to 26.22%, with a speedup by about 1.74x to 4.14x, compared to the baselines.