FedGraft: Memory-aware heterogeneous federated learning via model grafting
Publication Type
Journal Article
Publication Date
7-2025
Abstract
Although Federated Learning (FL) is good at collaborative learning among devices without compromising their data privacy, it suffers from the problem of large-scale deployment in Mobile Edge Computing (MEC) applications. This is mainly because the varying memory sizes of edge devices inevitably result in limited sizes of their hosting models. According to the Cannikin Law, when dealing with heterogeneous devices with different memory sizes, the learning capability of existing homogeneous FL schemes is greatly restricted by the weakest device. Worse still, although existing heterogeneous FL methods enable a MEC application to involve numerous devices equipped with heterogeneous models, their knowledge aggregation processes require either extra training data or architecture similarity of models. To address the above issues, this paper presents a novel FL method named FedGraft that enables effective knowledge sharing among heterogeneous device models of different sizes without imposing unrealistic assumptions. In FedGraft, all the device models are grafted to a common rootstock based on our proposed model partitioning and grafting mechanism, facilitating knowledge sharing among heterogeneous models on top of a tree-like global model. Meanwhile, using our proposed device selection strategy, the reassembled submodels extracted from the global model can be reasonably dispatched to corresponding devices with sufficient memory, thus enhancing the overall FL performance. Comprehensive experimental results show that, compared with state-of-the-art heterogeneous FL methods, FedGraft can improve inference accuracy by up to 17% in various memory-constrained scenarios.
Keywords
Training, Computational Modeling, Adaptation Models, Servers, Federated Learning, Data Models, Training Data, Feature Extraction, Performance Evaluation, Data Privacy, Federated Learning
Discipline
Numerical Analysis and Scientific Computing
Research Areas
Intelligent Systems and Optimization
Publication
IEEE Transactions on Mobile Computing
First Page
1
Last Page
13
ISSN
1536-1233
Identifier
10.1109/TMC.2025.3591537
Publisher
Institute of Electrical and Electronics Engineers
Citation
LIU, Ruixuan; HU, Ming; XIA, Zeke; XIE, Xiaofei; XIA, Jun; ZHANG, Pengyu; HUANG, Yihao; and CHEN, Mingsong.
FedGraft: Memory-aware heterogeneous federated learning via model grafting. (2025). IEEE Transactions on Mobile Computing. 1-13.
Available at: https://ink.library.smu.edu.sg/sis_research/10352
Additional URL
https://doi.org/10.1109/TMC.2025.3591537