# A Resource-Adaptive Approach for Federated Learning under Resource-Constrained Environments

arXiv: https://arxiv.org/abs/2406.13351 · HTML: https://mlsanity.com/paper/2406.13351/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 27 references that are in the map.
- First posted on arXiv 19 Jun 2024.

## Builds on (most cited first, 18 of 18)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [Federated Optimization in Heterogeneous Networks](https://mlsanity.com/paper/1812.06127/) (2018)
- [GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding](https://mlsanity.com/paper/2006.16668/) (2020)
- [Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training](https://mlsanity.com/paper/1712.01887/) (2017)
- [HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clients](https://mlsanity.com/paper/2010.01264/) (2020)
- [SplitFed: When Federated Learning Meets Split Learning](https://mlsanity.com/paper/2004.12088/) (2020)
- [Asynchronous Federated Optimization](https://mlsanity.com/paper/1903.03934/) (2019)
- [Model Pruning Enables Efficient Federated Learning on Edge Devices](https://mlsanity.com/paper/1909.12326/) (2019)
- [Efficient Large Scale Language Modeling with Mixtures of Experts](https://mlsanity.com/paper/2112.10684/) (2021)
- [Distributed Learning of Deep Neural Networks using Independent Subnet Training](https://mlsanity.com/paper/1910.02120/) (2019)
- [Modeling Other Players with Bayesian Beliefs for Games with Incomplete Information](https://mlsanity.com/paper/2405.14122/) (2024)
- [Resource Allocation in Large Language Model Integrated 6G Vehicular Networks](https://mlsanity.com/paper/2403.19016/) (2024)
- [Online Model Compression for Federated Learning with Large Models](https://mlsanity.com/paper/2205.03494/) (2022)
- [Collaborative AI Teaming in Unknown Environments via Active Goal Deduction](https://mlsanity.com/paper/2403.15341/) (2024)
- [Cooperative Backdoor Attack in Decentralized Reinforcement Learning with Theoretical Guarantee](https://mlsanity.com/paper/2405.15245/) (2024)
- [Split Two-Tower Model for Efficient and Privacy-Preserving Cross-device Federated Recommendation](https://mlsanity.com/paper/2206.13715/) (2022)
- [FedDCT: Federated Learning of Large Convolutional Neural Networks on Resource Constrained Devices using Divide and Collaborative Training](https://mlsanity.com/paper/2211.10948/) (2022)

## Built on by (most cited first, 1 of 1)

- [RefProtoFL: Communication-Efficient Federated Learning via External-Referenced Prototype Alignment](https://mlsanity.com/paper/2601.14746/) (2026)

## Abstract (arXiv)

The paper studies a fundamental federated learning (FL) problem involving multiple clients with heterogeneous constrained resources. Compared with the numerous training parameters, the computing and communication resources of clients are insufficient for fast local training and real-time knowledge sharing. Besides, training on clients with heterogeneous resources may result in the straggler problem. To address these issues, we propose Fed-RAA: a Resource-Adaptive Asynchronous Federated learning algorithm. Different from vanilla FL methods, where all parameters are trained by each participating client regardless of resource diversity, Fed-RAA adaptively allocates fragments of the global model to clients based on their computing and communication capabilities. Each client then individually trains its assigned model fragment and asynchronously uploads the updated result. Theoretical analysis confirms the convergence of our approach. Additionally, we design an online greedy-based algorithm for fragment allocation in Fed-RAA, achieving fairness comparable to an offline strategy. We present numerical results on MNIST, CIFAR-10, and CIFAR-100, along with necessary comparisons and ablation studies, demonstrating the advantages of our work. To the best of our knowledge, this paper represents the first resource-adaptive asynchronous method for fragment-based FL with guaranteed theoretical convergence.