# FedConv: A Learning-on-Model Paradigm for Heterogeneous Federated Clients

arXiv: https://arxiv.org/abs/2502.20639 · HTML: https://mlsanity.com/paper/2502.20639/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 86 references that are in the map.
- First posted on arXiv 28 Feb 2025.

## Builds on (most cited first, 30 of 34)

- [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)
- [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)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [How transferable are features in deep neural networks?](https://mlsanity.com/paper/1411.1792/) (2014)
- [Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification](https://mlsanity.com/paper/1909.06335/) (2019)
- [Ensemble Distillation for Robust Model Fusion in Federated Learning](https://mlsanity.com/paper/2006.07242/) (2020)
- [Personalized Federated Learning with Moreau Envelopes](https://mlsanity.com/paper/2006.08848/) (2020)
- [Rethinking the Value of Network Pruning](https://mlsanity.com/paper/1810.05270/) (2018)
- [FedMD: Heterogenous Federated Learning via Model Distillation](https://mlsanity.com/paper/1910.03581/) (2019)
- [Flower: A Friendly Federated Learning Research Framework](https://mlsanity.com/paper/2007.14390/) (2020)
- [Data-Free Knowledge Distillation for Heterogeneous Federated Learning](https://mlsanity.com/paper/2105.10056/) (2021)
- [Snapshot Ensembles: Train 1, get M for free](https://mlsanity.com/paper/1704.00109/) (2017)
- [HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clients](https://mlsanity.com/paper/2010.01264/) (2020)
- [A guide to convolution arithmetic for deep learning](https://mlsanity.com/paper/1603.07285/) (2016)
- [FedHealth: A Federated Transfer Learning Framework for Wearable Healthcare](https://mlsanity.com/paper/1907.09173/) (2019)
- [Parameterized Knowledge Transfer for Personalized Federated Learning](https://mlsanity.com/paper/2111.02862/) (2021)
- [FedRolex: Model-Heterogeneous Federated Learning with Rolling Sub-Model Extraction](https://mlsanity.com/paper/2212.01548/) (2022)
- [8-Bit Approximations for Parallelism in Deep Learning](https://mlsanity.com/paper/1511.04561/) (2015)
- [FedBalancer: Data and Pace Control for Efficient Federated Learning on Heterogeneous Clients](https://mlsanity.com/paper/2201.01601/) (2022)
- [Pixel Recursive Super Resolution](https://mlsanity.com/paper/1702.00783/) (2017)
- [Federated Transfer Learning: concept and applications](https://mlsanity.com/paper/2010.15561/) (2020)
- [Towards Model Agnostic Federated Learning Using Knowledge Distillation](https://mlsanity.com/paper/2110.15210/) (2021)
- [Personalized Federated Learning by Structured and Unstructured Pruning under Data Heterogeneity](https://mlsanity.com/paper/2105.00562/) (2021)
- [FedAdapter: Efficient Federated Learning for Modern NLP](https://mlsanity.com/paper/2205.10162/) (2022)
- [Federated Few-Shot Learning for Mobile NLP](https://mlsanity.com/paper/2212.05974/) (2022)
- [SiFall: Practical Online Fall Detection with RF Sensing](https://mlsanity.com/paper/2301.03773/) (2023)
- [Federated Learning with Nesterov Accelerated Gradient](https://mlsanity.com/paper/2009.08716/) (2020)

## Built on by (most cited first, 7 of 7)

- [AutoIOT: LLM-Driven Automated Natural Language Programming for AIoT Applications](https://mlsanity.com/paper/2503.05346/) (2025)
- [GPIoT: Tailoring Small Language Models for IoT Program Synthesis and Development](https://mlsanity.com/paper/2503.00686/) (2025)
- [Towards Privacy-Preserving and Personalized Smart Homes via Tailored Small Language Models](https://mlsanity.com/paper/2507.08878/) (2025)
- [Hypernetworks for Model-Heterogeneous Personalized Federated Learning](https://mlsanity.com/paper/2507.22330/) (2025)
- [Optimizing Storage Overhead of User Behavior Log for ML-embedded Mobile Apps](https://mlsanity.com/paper/2510.13405/) (2025)
- [Optimizing Feature Extraction for On-device Model Inference with User Behavior Sequences](https://mlsanity.com/paper/2603.21508/) (2026)
- [NeuroPath: Practically Adopting Motor Imagery Decoding through EEG Signals](https://mlsanity.com/paper/2604.09654/) (2026)

## Abstract (arXiv)

Federated Learning (FL) facilitates collaborative training of a shared global model without exposing clients' private data. In practical FL systems, clients (e.g., edge servers, smartphones, and wearables) typically have disparate system resources. Conventional FL, however, adopts a one-size-fits-all solution, where a homogeneous large global model is transmitted to and trained on each client, resulting in an overwhelming workload for less capable clients and starvation for other clients. To address this issue, we propose FedConv, a client-friendly FL framework, which minimizes the computation and memory burden on resource-constrained clients by providing heterogeneous customized sub-models. FedConv features a novel learning-on-model paradigm that learns the parameters of the heterogeneous sub-models via convolutional compression. Unlike traditional compression methods, the compressed models in FedConv can be directly trained on clients without decompression. To aggregate the heterogeneous sub-models, we propose transposed convolutional dilation to convert them back to large models with a unified size while retaining personalized information from clients. The compression and dilation processes, transparent to clients, are optimized on the server leveraging a small public dataset. Extensive experiments on six datasets demonstrate that FedConv outperforms state-of-the-art FL systems in terms of model accuracy (by more than 35% on average), computation and communication overhead (with 33% and 25% reduction, respectively).