# Splitfed learning without client-side synchronization: Analyzing client-side split network portion size to overall performance

arXiv: https://arxiv.org/abs/2109.09246 · HTML: https://mlsanity.com/paper/2109.09246/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 15 references that are in the map.
- First posted on arXiv 19 Sep 2021.

## Builds on (most cited first, 7 of 7)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Federated Learning: Challenges, Methods, and Future Directions](https://mlsanity.com/paper/1908.07873/) (2019)
- [Federated Learning: Strategies for Improving Communication Efficiency](https://mlsanity.com/paper/1610.05492/) (2016)
- [SplitFed: When Federated Learning Meets Split Learning](https://mlsanity.com/paper/2004.12088/) (2020)
- [Detailed comparison of communication efficiency of split learning and federated learning](https://mlsanity.com/paper/1909.09145/) (2019)
- [Split Learning for collaborative deep learning in healthcare](https://mlsanity.com/paper/1912.12115/) (2019)
- [Advancements of federated learning towards privacy preservation: from federated learning to split learning](https://mlsanity.com/paper/2011.14818/) (2020)

## Built on by (most cited first, 11 of 11)

- [Efficient Parallel Split Learning over Resource-constrained Wireless Edge Networks](https://mlsanity.com/paper/2303.15991/) (2023)
- [Split Learning in 6G Edge Networks](https://mlsanity.com/paper/2306.12194/) (2023)
- [Combined Federated and Split Learning in Edge Computing for Ubiquitous Intelligence in Internet of Things: State of the Art and Future Directions](https://mlsanity.com/paper/2207.09611/) (2022)
- [Model Partition and Resource Allocation for Split Learning in Vehicular Edge Networks](https://mlsanity.com/paper/2411.06773/) (2024)
- [SLPerf: a Unified Framework for Benchmarking Split Learning](https://mlsanity.com/paper/2304.01502/) (2023)
- [A Novel Collaborative Framework for Efficient Synchronization in Split Federated Learning over Wireless Networks](https://mlsanity.com/paper/2503.15559/) (2025)
- [CycleSL: Server-Client Cyclical Update Driven Scalable Split Learning](https://mlsanity.com/paper/2511.18611/) (2025)
- [Non-Federated Multi-Task Split Learning for Heterogeneous Sources](https://mlsanity.com/paper/2406.00150/) (2024)
- [Integration of TinyML and LargeML: A Survey of 6G and Beyond](https://mlsanity.com/paper/2505.15854/) (2025)
- [GAPSL: A Gradient-Aligned Parallel Split Learning over Data-Heterogeneous Edge Computing Systems](https://mlsanity.com/paper/2603.18540/) (2026)
- [A Survey on Split Learning for LLM Fine-Tuning: Models, Systems, and Privacy Optimizations](https://mlsanity.com/paper/2604.24468/) (2026)

## Abstract (arXiv)

Federated Learning (FL), Split Learning (SL), and SplitFed Learning (SFL) are three recent developments in distributed machine learning that are gaining attention due to their ability to preserve the privacy of raw data. Thus, they are widely applicable in various domains where data is sensitive, such as large-scale medical image classification, internet-of-medical-things, and cross-organization phishing email detection. SFL is developed on the confluence point of FL and SL. It brings the best of FL and SL by providing parallel client-side machine learning model updates from the FL paradigm and a higher level of model privacy (while training) by splitting the model between the clients and server coming from SL. However, SFL has communication and computation overhead at the client-side due to the requirement of client-side model synchronization. For the resource-constrained client-side, removal of such requirements is required to gain efficiency in the learning. In this regard, this paper studies SFL without client-side model synchronization. The resulting architecture is known as Multi-head Split Learning. Our empirical studies considering the ResNet18 model on MNIST data under IID data distribution among distributed clients find that Multi-head Split Learning is feasible. Its performance is comparable to the SFL. Moreover, SFL provides only 1%-2% better accuracy than Multi-head Split Learning on the MNIST test set. To further strengthen our results, we study the Multi-head Split Learning with various client-side model portions and its impact on the overall performance. To this end, our results find a minimal impact on the overall performance of the model.