Layer-wised Model Aggregation for Personalized Federated Learning
Open accessThe DOI matches its Crossref record; 41 of the 41 references it cites were found in a registry or an index.
Abstract
Personalized Federated Learning (pFL) not only can capture the common priors from broad range of distributed data, but also support customized models for heterogeneous clients. Researches over the past few years have applied the weighted aggregation manner to produce personalized models, where the weights are determined by calibrating the distance of the entire model parameters or loss values, and have yet to consider the layer-level impacts to the aggregation process, leading to lagged model convergence and inadequate personalization over non-IID datasets. In this paper, we propose a novel pFL training framework dubbed Layer-wised Personalized Federated learning (pFedLA) that can discern the importance of each layer from different clients, and thus is able to optimize the personalized model aggregation for clients with heterogeneous data. Specifically, we employ a dedicated hyper-network per client on the server side, which is trained to identify the mutual contribution factors at layer granularity. Meanwhile, a parameterized mechanism is introduced to update the layer-wised aggregation weights to progressively exploit the inter-user similarity and realize accurate model personalization. Extensive experiments are conducted over different models and learning tasks, and we show that the proposed methods achieve significantly higher performance than state-of-the-art pFL methods.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Federated Optimization in Heterogeneous Networks
Li, T., Sahu, A. K., Zaheer, M., Sanjabi, M., Talwalkar, A., & Smith, V. (2018) · arXiv · doi:10.48550/arxiv.1812.06127 · Cited by 4,023
Federated Learning with Non-IID Data
Zhao, Y., Li, M., Lai, L., Suda, N., Civin, D., & Chandra, V. (2018) · arXiv · doi:10.48550/arxiv.1806.00582 · Cited by 2,077 · cited 2×
“The typical way of data-based pFL is to share a small amount of global data to each client [56].”
BackgroundPersonalized Federated Learning with Theoretical Guarantees: A Model-Agnostic Meta-Learning Approach
Fallah, A., Mokhtari, A., & Ozdaglar, A. (2020) · neural information processing systems · Cited by 1,635
Yu, F., Wang, D., Shelhamer, E., & Darrell, T. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00255 · Cited by 1,516
Federated Learning over Wireless Networks: Optimization Model Design and Analysis
Tran, N. H., Bao, W., Zomaya, A., Nguyen, M. N. H., & Hong, C. S. (2019) · IEEE INFOCOM 2019 - IEEE Conference on Computer Communications · doi:10.1109/infocom.2019.8737464 · Cited by 1,013
Optimizing Federated Learning on Non-IID Data with Reinforcement Learning
Wang, H., Kaplan, Z., Niu, D., & Li, B. (2020) · IEEE INFOCOM 2020 - IEEE Conference on Computer Communications · doi:10.1109/infocom41043.2020.9155494 · Cited by 981
Personalized Cross-Silo Federated Learning on Non-IID Data
Huang, Y., Chu, L., Zhou, Z., Wang, L., Liu, J., Pei, J., & Zhang, Y. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i9.16960 · Cited by 723 · cited 6×
“, FedAMP [15], FedFomo [54], MOCHA [39], KT-pFL [51] etc.”
BackgroundMethodInfluentialAn Efficient Framework for Clustered Federated Learning
Ghosh, A., Chung, J., Yin, D., & Ramchandran, K. (2022) · IEEE Transactions on Information Theory · doi:10.1109/tit.2022.3192506 · Cited by 623 · cited 1×
“Some researchers [10, 15, 32] propose to train multiple global models at the server, where similar clients are clustered into several groups and different models are trained for each group.”
BackgroundFederated Learning with Personalization Layers
Arivazhagan, M. G., Aggarwal, V., Singh, A. K., & Choudhary, S. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.00818 · Cited by 495 · cited 1×
“Singlemodel based methods extended from the conventional FL algorithms like FedAvg [33] combine the optimization of the local models and global model, which consist of five different kinds of approaches: local fine-tuning [1,36,46], regularization [12,13,41], model mixture [7,32], meta learning [9, 18] and parameter d…”
MethodJeong, E., Oh, S., Kim, H., Park, J., Bennis, M., & Kim, S.-L. (2018) · arXiv · doi:10.48550/arxiv.1811.11479 · Cited by 465 · cited 2×
“[8,16] focus on data augmentation methods by generating additional data to augment its local data towards yielding an IID dataset.”
BackgroundMethod
Cited by
Federated learning for healthcare applications
Chaddad, A., Wu, Y., & Desrosiers, C. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3325822 · Cited by 136
“To address the issue of non-IID data across different clients, the approach in [32] trains personalized models using chan-nelwise assignment instead of the layerwise personalization techniques of previous studies [57], [58], [59], [60].”
MethodFederated Transfer–Ordered–Personalized Learning for Driver Monitoring Application
Yuan, L., Su, L., & Wang, Z. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3279273 · Cited by 40
“Ma et al. [31] proposed a personalized FL framework of layer-wised weighted aggregation, which determines mutual contribution factors through a hypernetwork on the server to identify similarity between users at the layer granularity.”
Background
Metadata
- Authors
- Ma, X., Zhang, J., Guo, S., & Xu, W.
- Venue
- 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2022-06
- Pages
- 10082-10091
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W4312634912
- Cited by
- 240
- References
- 41
- FWCI
- 30.55
- Type
- conference paper
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.