# AnycostFL: Efficient On-Demand Federated Learning over Heterogeneous Edge Devices

arXiv: https://arxiv.org/abs/2301.03062 · HTML: https://mlsanity.com/paper/2301.03062/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 51 references that are in the map.
- First posted on arXiv 8 Jan 2023.

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

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Convex optimization](https://mlsanity.com/paper/2106.01946/) (2021)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [Federated Learning: Strategies for Improving Communication Efficiency](https://mlsanity.com/paper/1610.05492/) (2016)
- [Ensemble Distillation for Robust Model Fusion in Federated Learning](https://mlsanity.com/paper/2006.07242/) (2020)
- [Federated Learning with Matched Averaging](https://mlsanity.com/paper/2002.06440/) (2020)
- [Robust and Communication-Efficient Federated Learning from Non-IID Data](https://mlsanity.com/paper/1903.02891/) (2019)
- [Data-Free Knowledge Distillation for Heterogeneous Federated Learning](https://mlsanity.com/paper/2105.10056/) (2021)
- [FedPAQ: A Communication-Efficient Federated Learning Method with Periodic Averaging and Quantization](https://mlsanity.com/paper/1909.13014/) (2019)
- [Client Selection for Federated Learning with Heterogeneous Resources in Mobile Edge](https://mlsanity.com/paper/1804.08333/) (2018)
- [HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clients](https://mlsanity.com/paper/2010.01264/) (2020)
- [A Joint Learning and Communications Framework for Federated Learning over Wireless Networks](https://mlsanity.com/paper/1909.07972/) (2019)
- [Client-Edge-Cloud Hierarchical Federated Learning](https://mlsanity.com/paper/1905.06641/) (2019)
- [Energy Efficient Federated Learning Over Wireless Communication Networks](https://mlsanity.com/paper/1911.02417/) (2019)
- [UVeQFed: Universal Vector Quantization for Federated Learning](https://mlsanity.com/paper/2006.03262/) (2020)
- [Federated Learning over Wireless Networks: Convergence Analysis and Resource Allocation](https://mlsanity.com/paper/1910.13067/) (2019)
- [Joint Device Scheduling and Resource Allocation for Latency Constrained Wireless Federated Learning](https://mlsanity.com/paper/2007.07174/) (2020)
- [Adaptive Gradient Sparsification for Efficient Federated Learning: An Online Learning Approach](https://mlsanity.com/paper/2001.04756/) (2020)
- [Convergence Time Optimization for Federated Learning over Wireless Networks](https://mlsanity.com/paper/2001.07845/) (2020)
- [Privacy For Free: Wireless Federated Learning Via Uncoded Transmission With Adaptive Power Control](https://mlsanity.com/paper/2006.05459/) (2020)
- [To Talk or to Work: Flexible Communication Compression for Energy Efficient Federated Learning over Heterogeneous Mobile Edge Devices](https://mlsanity.com/paper/2012.11804/) (2020)
- [Device Sampling for Heterogeneous Federated Learning: Theory, Algorithms, and Implementation](https://mlsanity.com/paper/2101.00787/) (2021)
- [Optimal Rate Adaption in Federated Learning with Compressed Communications](https://mlsanity.com/paper/2112.06694/) (2021)
- [Joint Superposition Coding and Training for Federated Learning over Multi-Width Neural Networks](https://mlsanity.com/paper/2112.02543/) (2021)
- [Bandwidth Allocation for Multiple Federated Learning Services in Wireless Edge Networks](https://mlsanity.com/paper/2101.03627/) (2021)
- [FedGreen: Federated Learning with Fine-Grained Gradient Compression for Green Mobile Edge Computing](https://mlsanity.com/paper/2111.06146/) (2021)

## Built on by (most cited first, 10 of 10)

- [Filling the Missing: Exploring Generative AI for Enhanced Federated Learning over Heterogeneous Mobile Edge Devices](https://mlsanity.com/paper/2310.13981/) (2023)
- [Federated Learning While Providing Model as a Service: Joint Training and Inference Optimization](https://mlsanity.com/paper/2312.12863/) (2023)
- [Federated learning compression designed for lightweight communications](https://mlsanity.com/paper/2310.14693/) (2023)
- [Heterogeneity-aware Personalized Federated Learning via Adaptive Dual-Agent Reinforcement Learning](https://mlsanity.com/paper/2501.16966/) (2025)
- [An Information-Theoretic Analysis for Federated Learning under Concept Drift](https://mlsanity.com/paper/2506.21036/) (2025)
- [FedGreen: Carbon-aware Federated Learning with Model Size Adaptation](https://mlsanity.com/paper/2404.15503/) (2024)
- [Heterogeneity-Aware Resource Allocation and Topology Design for Hierarchical Federated Edge Learning](https://mlsanity.com/paper/2409.19509/) (2024)
- [Computation-aware Energy-harvesting Federated Learning with Pipelined Cyclic Scheduling](https://mlsanity.com/paper/2511.11949/) (2025)
- [Spiking Personalized Federated Learning for Brain-Computer Interface-Enabled Immersive Communication](https://mlsanity.com/paper/2603.22727/) (2026)
- [A Methodology to Assess Power Modeling in Energy-Aware Federated Learning on Heterogeneous Mobile Devices](https://mlsanity.com/paper/2605.27601/) (2026)

## Abstract (arXiv)

In this work, we investigate the challenging problem of on-demand federated learning (FL) over heterogeneous edge devices with diverse resource constraints. We propose a cost-adjustable FL framework, named AnycostFL, that enables diverse edge devices to efficiently perform local updates under a wide range of efficiency constraints. To this end, we design the model shrinking to support local model training with elastic computation cost, and the gradient compression to allow parameter transmission with dynamic communication overhead. An enhanced parameter aggregation is conducted in an element-wise manner to improve the model performance. Focusing on AnycostFL, we further propose an optimization design to minimize the global training loss with personalized latency and energy constraints. By revealing the theoretical insights of the convergence analysis, personalized training strategies are deduced for different devices to match their locally available resources. Experiment results indicate that, when compared to the state-of-the-art efficient FL algorithms, our learning framework can reduce up to 1.9 times of the training latency and energy consumption for realizing a reasonable global testing accuracy. Moreover, the results also demonstrate that, our approach significantly improves the converged global accuracy.