# AdaptiveFL: Adaptive Heterogeneous Federated Learning for Resource-Constrained AIoT Systems

arXiv: https://arxiv.org/abs/2311.13166 · HTML: https://mlsanity.com/paper/2311.13166/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 20 references that are in the map.
- First posted on arXiv 22 Nov 2023.

## Builds on (most cited first, 12 of 12)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [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)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Pruning Filters for Efficient ConvNets](https://mlsanity.com/paper/1608.08710/) (2016)
- [LEAF: A Benchmark for Federated Settings](https://mlsanity.com/paper/1812.01097/) (2018)
- [Ensemble Distillation for Robust Model Fusion in Federated Learning](https://mlsanity.com/paper/2006.07242/) (2020)
- [Unifying Count-Based Exploration and Intrinsic Motivation](https://mlsanity.com/paper/1606.01868/) (2016)
- [HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clients](https://mlsanity.com/paper/2010.01264/) (2020)
- [Heterogeneous Ensemble Knowledge Transfer for Training Large Models in Federated Learning](https://mlsanity.com/paper/2204.12703/) (2022)
- [GitFL: Adaptive Asynchronous Federated Learning using Version Control](https://mlsanity.com/paper/2211.12049/) (2022)
- [FedAIoT: A Federated Learning Benchmark for Artificial Intelligence of Things](https://mlsanity.com/paper/2310.00109/) (2023)

## Built on by (most cited first, 9 of 9)

- [CaBaFL: Asynchronous Federated Learning via Hierarchical Cache and Feature Balance](https://mlsanity.com/paper/2404.12850/) (2024)
- [EFTViT: Efficient Federated Training of Vision Transformers with Masked Images on Resource-Constrained Clients](https://mlsanity.com/paper/2412.00334/) (2024)
- [Learnable Sparse Customization in Heterogeneous Edge Computing](https://mlsanity.com/paper/2412.07216/) (2024)
- [Accelerated Training on Low-Power Edge Devices](https://mlsanity.com/paper/2502.18323/) (2025)
- [Energy and Memory-Efficient Federated Learning With Ordered Layer Freezing](https://mlsanity.com/paper/2512.23200/) (2025)
- [SubFLOT: Submodel Extraction for Efficient and Personalized Federated Learning via Optimal Transport](https://mlsanity.com/paper/2604.06631/) (2026)
- [FedQP: Towards Accurate Federated Learning using Quadratic Programming Guided Mutation](https://mlsanity.com/paper/2411.15847/) (2024)
- [QA-HFL: Quality-Aware Hierarchical Federated Learning for Resource-Constrained Mobile Devices with Heterogeneous Image Quality](https://mlsanity.com/paper/2506.05411/) (2025)
- [Gradients as an Action: Towards Communication-Efficient Federated Recommender Systems via Adaptive Action Sharing](https://mlsanity.com/paper/2507.08842/) (2025)

## Abstract (arXiv)

Although Federated Learning (FL) is promising to enable collaborative learning among Artificial Intelligence of Things (AIoT) devices, it suffers from the problem of low classification performance due to various heterogeneity factors (e.g., computing capacity, memory size) of devices and uncertain operating environments. To address these issues, this paper introduces an effective FL approach named AdaptiveFL based on a novel fine-grained width-wise model pruning strategy, which can generate various heterogeneous local models for heterogeneous AIoT devices. By using our proposed reinforcement learning-based device selection mechanism, AdaptiveFL can adaptively dispatch suitable heterogeneous models to corresponding AIoT devices on the fly based on their available resources for local training. Experimental results show that, compared to state-of-the-art methods, AdaptiveFL can achieve up to 16.83% inference improvements for both IID and non-IID scenarios.