# Semi-Federated Learning: Convergence Analysis and Optimization of A Hybrid Learning Framework

arXiv: https://arxiv.org/abs/2310.02559 · HTML: https://mlsanity.com/paper/2310.02559/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 58 references that are in the map.
- First posted on arXiv 4 Oct 2023.

## Builds on (most cited first, 28 of 28)

- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Convex optimization](https://mlsanity.com/paper/2106.01946/) (2021)
- [Federated Learning in Mobile Edge Networks: A Comprehensive Survey](https://mlsanity.com/paper/1909.11875/) (2019)
- [A Joint Learning and Communications Framework for Federated Learning over Wireless Networks](https://mlsanity.com/paper/1909.07972/) (2019)
- [Federated Learning via Over-the-Air Computation](https://mlsanity.com/paper/1812.11750/) (2018)
- [Broadband Analog Aggregation for Low-Latency Federated Edge Learning (Extended Version)](https://mlsanity.com/paper/1812.11494/) (2018)
- [Distributed Learning in Wireless Networks: Recent Progress and Future Challenges](https://mlsanity.com/paper/2104.02151/) (2021)
- [One-Bit Over-the-Air Aggregation for Communication-Efficient Federated Edge Learning: Design and Convergence Analysis](https://mlsanity.com/paper/2001.05713/) (2020)
- [Federated Learning for Edge Networks: Resource Optimization and Incentive Mechanism](https://mlsanity.com/paper/1911.05642/) (2019)
- [Communication-Efficient and Distributed Learning Over Wireless Networks: Principles and Applications](https://mlsanity.com/paper/2008.02608/) (2020)
- [Blind Federated Edge Learning](https://mlsanity.com/paper/2010.10030/) (2020)
- [Reconfigurable Intelligent Surface Enabled Federated Learning: A Unified Communication-Learning Design Approach](https://mlsanity.com/paper/2011.10282/) (2020)
- [Mix2FLD: Downlink Federated Learning After Uplink Federated Distillation With Two-Way Mixup](https://mlsanity.com/paper/2006.09801/) (2020)
- [Convergence Analysis and System Design for Federated Learning over Wireless Networks](https://mlsanity.com/paper/2105.00872/) (2021)
- [Integrating Over-the-Air Federated Learning and Non-Orthogonal Multiple Access: What Role can RIS Play?](https://mlsanity.com/paper/2103.00435/) (2021)
- [Joint Optimization of Communications and Federated Learning Over the Air](https://mlsanity.com/paper/2104.03490/) (2021)
- [A Hybrid Architecture for Federated and Centralized Learning](https://mlsanity.com/paper/2105.03288/) (2021)
- [STAR-RIS Integrated Non-Orthogonal Multiple Access and Over-the-Air Federated Learning: Framework, Analysis, and Optimization](https://mlsanity.com/paper/2106.08592/) (2021)
- [Balancing Accuracy and Integrity for Reconfigurable Intelligent Surface-aided Over-the-Air Federated Learning](https://mlsanity.com/paper/2207.08057/) (2022)
- [Federated Learning in Multi-RIS Aided Systems](https://mlsanity.com/paper/2010.13333/) (2020)
- [Semi-Federated Learning for Collaborative Intelligence in Massive IoT Networks](https://mlsanity.com/paper/2303.05048/) (2023)
- [AirMixML: Over-the-Air Data Mixup for Inherently Privacy-Preserving Edge Machine Learning](https://mlsanity.com/paper/2105.00395/) (2021)
- [A Fast Blockchain-based Federated Learning Framework with Compressed Communications](https://mlsanity.com/paper/2208.06095/) (2022)
- [Resource Allocation for Multi-Cell IRS-Aided NOMA Networks](https://mlsanity.com/paper/2006.11811/) (2020)
- [Intelligent Reflecting Surface Aided MISO Uplink Communication Network: Feasibility and Power Minimization for Perfect and Imperfect CSI](https://mlsanity.com/paper/2011.11856/) (2020)
- [Optimal Resource Allocation for Delay Minimization in NOMA-MEC Networks](https://mlsanity.com/paper/2009.06397/) (2020)
- [Over-the-Air Computation via Broadband Channels](https://mlsanity.com/paper/2106.02243/) (2021)
- [Wireless Federated Learning over MIMO Networks: Joint Device Scheduling and Beamforming Design](https://mlsanity.com/paper/2111.00470/) (2021)

## Abstract (arXiv)

Under the organization of the base station (BS), wireless federated learning (FL) enables collaborative model training among multiple devices. However, the BS is merely responsible for aggregating local updates during the training process, which incurs a waste of the computational resource at the BS. To tackle this issue, we propose a semi-federated learning (SemiFL) paradigm to leverage the computing capabilities of both the BS and devices for a hybrid implementation of centralized learning (CL) and FL. Specifically, each device sends both local gradients and data samples to the BS for training a shared global model. To improve communication efficiency over the same time-frequency resources, we integrate over-the-air computation for aggregation and non-orthogonal multiple access for transmission by designing a novel transceiver structure. To gain deep insights, we conduct convergence analysis by deriving a closed-form optimality gap for SemiFL and extend the result to two extra cases. In the first case, the BS uses all accumulated data samples to calculate the CL gradient, while a decreasing learning rate is adopted in the second case. Our analytical results capture the destructive effect of wireless communication and show that both FL and CL are special cases of SemiFL. Then, we formulate a non-convex problem to reduce the optimality gap by jointly optimizing the transmit power and receive beamformers. Accordingly, we propose a two-stage algorithm to solve this intractable problem, in which we provide the closed-form solutions to the beamformers. Extensive simulation results on two real-world datasets corroborate our theoretical analysis, and show that the proposed SemiFL outperforms conventional FL and achieves 3.2% accuracy gain on the MNIST dataset compared to state-of-the-art benchmarks.