mlsanityData to 7 Oct 2026

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

arXiv 2502.20639 ↗First posted 28 Feb 2025cs.LG cs.AIcited by 7

Not on the map. Why?

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).

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

Builds on

34 of 86 references.

References · 34

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  5. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  6. 2013Visualizing and Understanding Convolutional Networkscited by 2,278
  7. 2014How transferable are features in deep neural networks?cited by 1,216
  8. 2019Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classificationcited by 836
  9. 2020Ensemble Distillation for Robust Model Fusion in Federated Learningcited by 678
  10. 2020Personalized Federated Learning with Moreau Envelopescited by 612
  11. 2018Rethinking the Value of Network Pruningcited by 595
  12. 2019FedMD: Heterogenous Federated Learning via Model Distillationcited by 454
22 more
  1. 2020Flower: A Friendly Federated Learning Research Frameworkcited by 449
  2. 2021Data-Free Knowledge Distillation for Heterogeneous Federated Learningcited by 380
  3. 2017Snapshot Ensembles: Train 1, get M for freecited by 349
  4. 2020HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clientscited by 334
  5. 2016A guide to convolution arithmetic for deep learningcited by 182
  6. 2019FedHealth: A Federated Transfer Learning Framework for Wearable Healthcarecited by 182
  7. 2021Parameterized Knowledge Transfer for Personalized Federated Learningcited by 108
  8. 2022FedRolex: Model-Heterogeneous Federated Learning with Rolling Sub-Model Extractioncited by 102
  9. 20158-Bit Approximations for Parallelism in Deep Learningcited by 56
  10. 2022FedBalancer: Data and Pace Control for Efficient Federated Learning on Heterogeneous Clientscited by 46
  11. 2017Pixel Recursive Super Resolutioncited by 44
  12. 2020Federated Transfer Learning: concept and applicationscited by 32
  13. 2021Towards Model Agnostic Federated Learning Using Knowledge Distillationcited by 31
  14. 2021Personalized Federated Learning by Structured and Unstructured Pruning under Data Heterogeneitycited by 27
  15. 2022FedAdapter: Efficient Federated Learning for Modern NLPcited by 24
  16. 2022Federated Few-Shot Learning for Mobile NLPcited by 15
  17. 2023SiFall: Practical Online Fall Detection with RF Sensingcited by 15
  18. 2020Federated Learning with Nesterov Accelerated Gradientcited by 11
  19. 2023Cost-effective On-device Continual Learning over Memory Hierarchy with Mirocited by 10
  20. 2023Construct 3D Hand Skeleton with Commercial WiFicited by 10
  21. 2022Multi-Task and Transfer Learning for Federated Learning Applicationscited by 2
  22. 2023REPA: Client Clustering without Training and Data Labels for Improved Federated Learning in Non-IID Settingscited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 5; 2026: 2.

7 papers.

  1. 2025AutoIOT: LLM-Driven Automated Natural Language Programming for AIoT Applicationscited by 17
  2. 2025GPIoT: Tailoring Small Language Models for IoT Program Synthesis and Developmentcited by 10
  3. 2025Towards Privacy-Preserving and Personalized Smart Homes via Tailored Small Language Modelscited by 1
  4. 2025Hypernetworks for Model-Heterogeneous Personalized Federated Learningcited by 1
  5. 2025Optimizing Storage Overhead of User Behavior Log for ML-embedded Mobile Appscited by 1
  6. 2026Optimizing Feature Extraction for On-device Model Inference with User Behavior Sequencescited by 0
  7. 2026NeuroPath: Practically Adopting Motor Imagery Decoding through EEG Signalscited by 0