# FedRolex: Model-Heterogeneous Federated Learning with Rolling Sub-Model Extraction

arXiv: https://arxiv.org/abs/2212.01548 · HTML: https://mlsanity.com/paper/2212.01548/

## Key facts

- Cited by 102 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 34 references that are in the map.
- First posted on arXiv 3 Dec 2022.

## Builds on (most cited first, 26 of 26)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Advances and Open Problems in Federated Learning](https://mlsanity.com/paper/1912.04977/) (2019)
- [Federated Optimization in Heterogeneous Networks](https://mlsanity.com/paper/1812.06127/) (2018)
- [Ensemble Distillation for Robust Model Fusion in Federated Learning](https://mlsanity.com/paper/2006.07242/) (2020)
- [Federated Learning with Personalization Layers](https://mlsanity.com/paper/1912.00818/) (2019)
- [Ray: A Distributed Framework for Emerging AI Applications](https://mlsanity.com/paper/1712.05889/) (2017)
- [HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clients](https://mlsanity.com/paper/2010.01264/) (2020)
- [A Field Guide to Federated Optimization](https://mlsanity.com/paper/2107.06917/) (2021)
- [Attack of the Tails: Yes, You Really Can Backdoor Federated Learning](https://mlsanity.com/paper/2007.05084/) (2020)
- [FjORD: Fair and Accurate Federated Learning under heterogeneous targets with Ordered Dropout](https://mlsanity.com/paper/2102.13451/) (2021)
- [Does Knowledge Distillation Really Work?](https://mlsanity.com/paper/2106.05945/) (2021)
- [Practical Secure Aggregation for Federated Learning on User-Held Data](https://mlsanity.com/paper/1611.04482/) (2016)
- [FedBE: Making Bayesian Model Ensemble Applicable to Federated Learning](https://mlsanity.com/paper/2009.01974/) (2020)
- [Expanding the Reach of Federated Learning by Reducing Client Resource Requirements](https://mlsanity.com/paper/1812.07210/) (2018)
- [Learning Data Augmentation Strategies for Object Detection](https://mlsanity.com/paper/1906.11172/) (2019)
- [Distillation-Based Semi-Supervised Federated Learning for Communication-Efficient Collaborative Training with Non-IID Private Data](https://mlsanity.com/paper/2008.06180/) (2020)
- [Heterogeneous Ensemble Knowledge Transfer for Training Large Models in Federated Learning](https://mlsanity.com/paper/2204.12703/) (2022)
- [Siloed Federated Learning for Multi-Centric Histopathology Datasets](https://mlsanity.com/paper/2008.07424/) (2020)
- [Scaling Language Model Size in Cross-Device Federated Learning](https://mlsanity.com/paper/2204.09715/) (2022)
- [Partial Variable Training for Efficient On-Device Federated Learning](https://mlsanity.com/paper/2110.05607/) (2021)
- [Federated Select: A Primitive for Communication- and Memory-Efficient Federated Learning](https://mlsanity.com/paper/2208.09432/) (2022)

## Built on by (most cited first, 30 of 102)

- [SLoRA: Federated Parameter Efficient Fine-Tuning of Language Models](https://mlsanity.com/paper/2308.06522/) (2023)
- [FedGH: Heterogeneous Federated Learning with Generalized Global Header](https://mlsanity.com/paper/2303.13137/) (2023)
- [Federated Learning for Computationally-Constrained Heterogeneous Devices: A Survey](https://mlsanity.com/paper/2307.09182/) (2023)
- [pFedLoRA: Model-Heterogeneous Personalized Federated Learning with LoRA Tuning](https://mlsanity.com/paper/2310.13283/) (2023)
- [TimelyFL: Heterogeneity-aware Asynchronous Federated Learning with Adaptive Partial Training](https://mlsanity.com/paper/2304.06947/) (2023)
- [GPT-FL: Generative Pre-trained Model-Assisted Federated Learning](https://mlsanity.com/paper/2306.02210/) (2023)
- [DFRD: Data-Free Robustness Distillation for Heterogeneous Federated Learning](https://mlsanity.com/paper/2309.13546/) (2023)
- [Every Parameter Matters: Ensuring the Convergence of Federated Learning with Dynamic Heterogeneous Models Reduction](https://mlsanity.com/paper/2310.08670/) (2023)
- [pFedMoE: Data-Level Personalization with Mixture of Experts for Model-Heterogeneous Personalized Federated Learning](https://mlsanity.com/paper/2402.01350/) (2024)
- [Federated Model Heterogeneous Matryoshka Representation Learning](https://mlsanity.com/paper/2406.00488/) (2024)
- [FIARSE: Model-Heterogeneous Federated Learning via Importance-Aware Submodel Extraction](https://mlsanity.com/paper/2407.19389/) (2024)
- [A Survey for Federated Learning Evaluations: Goals and Measures](https://mlsanity.com/paper/2308.11841/) (2023)
- [Is Aggregation the Only Choice? Federated Learning via Layer-wise Model Recombination](https://mlsanity.com/paper/2305.10730/) (2023)
- [Multimodal Federated Learning in Healthcare: a Review](https://mlsanity.com/paper/2310.09650/) (2023)
- [FedP3: Federated Personalized and Privacy-friendly Network Pruning under Model Heterogeneity](https://mlsanity.com/paper/2404.09816/) (2024)
- [Advances in Robust Federated Learning: A Survey with Heterogeneity Considerations](https://mlsanity.com/paper/2405.09839/) (2024)
- [Agglomerative Federated Learning: Empowering Larger Model Training via End-Edge-Cloud Collaboration](https://mlsanity.com/paper/2312.11489/) (2023)
- [Breaking the Memory Wall for Heterogeneous Federated Learning via Progressive Training](https://mlsanity.com/paper/2404.13349/) (2024)
- [pFedES: Model Heterogeneous Personalized Federated Learning with Feature Extractor Sharing](https://mlsanity.com/paper/2311.06879/) (2023)
- [Effective Heterogeneous Federated Learning via Efficient Hypernetwork-based Weight Generation](https://mlsanity.com/paper/2407.03086/) (2024)
- [DapperFL: Domain Adaptive Federated Learning with Model Fusion Pruning for Edge Devices](https://mlsanity.com/paper/2412.05823/) (2024)
- [Maestro: Uncovering Low-Rank Structures via Trainable Decomposition](https://mlsanity.com/paper/2308.14929/) (2023)
- [FedAIoT: A Federated Learning Benchmark for Artificial Intelligence of Things](https://mlsanity.com/paper/2310.00109/) (2023)
- [A Comprehensive Survey of Federated Transfer Learning: Challenges, Methods and Applications](https://mlsanity.com/paper/2403.01387/) (2024)
- [Aggregating Capacity in FL through Successive Layer Training for Computationally-Constrained Devices](https://mlsanity.com/paper/2305.17005/) (2023)
- [FedConv: A Learning-on-Model Paradigm for Heterogeneous Federated Clients](https://mlsanity.com/paper/2502.20639/) (2025)
- [Towards a Better Theoretical Understanding of Independent Subnetwork Training](https://mlsanity.com/paper/2306.16484/) (2023)
- [Distributed Personalized Empirical Risk Minimization](https://mlsanity.com/paper/2310.17761/) (2023)
- [Why Go Full? Elevating Federated Learning Through Partial Network Updates](https://mlsanity.com/paper/2410.11559/) (2024)
- [Exploring Gradient Subspaces: Addressing and Overcoming LoRA's Limitations in Federated Fine-Tuning of Large Language Models](https://mlsanity.com/paper/2410.23111/) (2024)

## Abstract (arXiv)

Most cross-device federated learning (FL) studies focus on the model-homogeneous setting where the global server model and local client models are identical. However, such constraint not only excludes low-end clients who would otherwise make unique contributions to model training but also restrains clients from training large models due to on-device resource bottlenecks. In this work, we propose FedRolex, a partial training (PT)-based approach that enables model-heterogeneous FL and can train a global server model larger than the largest client model. At its core, FedRolex employs a rolling sub-model extraction scheme that allows different parts of the global server model to be evenly trained, which mitigates the client drift induced by the inconsistency between individual client models and server model architectures. We show that FedRolex outperforms state-of-the-art PT-based model-heterogeneous FL methods (e.g. Federated Dropout) and reduces the gap between model-heterogeneous and model-homogeneous FL, especially under the large-model large-dataset regime. In addition, we provide theoretical statistical analysis on its advantage over Federated Dropout and evaluate FedRolex on an emulated real-world device distribution to show that FedRolex can enhance the inclusiveness of FL and boost the performance of low-end devices that would otherwise not benefit from FL. Our code is available at: https://github.com/AIoT-MLSys-Lab/FedRolex