# Personalized Hierarchical Split Federated Learning in Wireless Networks

arXiv: https://arxiv.org/abs/2411.06042 · HTML: https://mlsanity.com/paper/2411.06042/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 26 references that are in the map.
- First posted on arXiv 9 Nov 2024.

## Builds on (most cited first, 19 of 19)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [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)
- [Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimization](https://mlsanity.com/paper/2007.07481/) (2020)
- [Federated Learning for Mobile Keyboard Prediction](https://mlsanity.com/paper/1811.03604/) (2018)
- [Split learning for health: Distributed deep learning without sharing raw patient data](https://mlsanity.com/paper/1812.00564/) (2018)
- [A Joint Learning and Communications Framework for Federated Learning over Wireless Networks](https://mlsanity.com/paper/1909.07972/) (2019)
- [FedBABU: Towards Enhanced Representation for Federated Image Classification](https://mlsanity.com/paper/2106.06042/) (2021)
- [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)
- [FedDisco: Federated Learning with Discrepancy-Aware Collaboration](https://mlsanity.com/paper/2305.19229/) (2023)
- [Big AI Models for 6G Wireless Networks: Opportunities, Challenges, and Research Directions](https://mlsanity.com/paper/2308.06250/) (2023)
- [Demystifying Why Local Aggregation Helps: Convergence Analysis of Hierarchical SGD](https://mlsanity.com/paper/2010.12998/) (2020)
- [SplitGP: Achieving Both Generalization and Personalization in Federated Learning](https://mlsanity.com/paper/2212.08343/) (2022)
- [Accelerating Split Federated Learning over Wireless Communication Networks](https://mlsanity.com/paper/2310.15584/) (2023)
- [Resource Constrained Vehicular Edge Federated Learning with Highly Mobile Connected Vehicles](https://mlsanity.com/paper/2210.15496/) (2022)
- [Hierarchical Federated Learning in Wireless Networks: Pruning Tackles Bandwidth Scarcity and System Heterogeneity](https://mlsanity.com/paper/2308.01562/) (2023)
- [ParallelSFL: A Novel Split Federated Learning Framework Tackling Heterogeneity Issues](https://mlsanity.com/paper/2410.01256/) (2024)
- [Resource-Aware Hierarchical Federated Learning in Wireless Video Caching Networks](https://mlsanity.com/paper/2402.04216/) (2024)

## Abstract (arXiv)

Extreme resource constraints make large-scale machine learning (ML) with distributed clients challenging in wireless networks. On the one hand, large-scale ML requires massive information exchange between clients and server(s). On the other hand, these clients have limited battery and computation powers that are often dedicated to operational computations. Split federated learning (SFL) is emerging as a potential solution to mitigate these challenges, by splitting the ML model into client-side and server-side model blocks, where only the client-side block is trained on the client device. However, practical applications require personalized models that are suitable for the client's personal task. Motivated by this, we propose a personalized hierarchical split federated learning (PHSFL) algorithm that is specially designed to achieve better personalization performance. More specially, owing to the fact that regardless of the severity of the statistical data distributions across the clients, many of the features have similar attributes, we only train the body part of the federated learning (FL) model while keeping the (randomly initialized) classifier frozen during the training phase. We first perform extensive theoretical analysis to understand the impact of model splitting and hierarchical model aggregations on the global model. Once the global model is trained, we fine-tune each client classifier to obtain the personalized models. Our empirical findings suggest that while the globally trained model with the untrained classifier performs quite similarly to other existing solutions, the fine-tuned models show significantly improved personalized performance.