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.”
BackgroundMethodBrabandere, B. D., Jia, X., Tuytelaars, T., & Gool, L. V. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1605.09673 · Cited by 461 · cited 1×
“Hypernetworks have been widely used in various machine learning applications, such as language modeling [35,40], computer vision [17,19,27], 3D scene representation [28, 38], hyperparameter optimization [2, 25, 29, 31], neural architecture search (NAS) [3, 50], continual learning [44] and…”
MethodSelf-Balancing Federated Learning With Global Imbalanced Data in Mobile Systems
Duan, M., Liu, D., Chen, X., Liu, R., Tan, Y., & Liang, L. (2021) · IEEE Transactions on Parallel and Distributed Systems · doi:10.1109/tpds.2020.3009406 · Cited by 432
Improving Federated Learning Personalization via Model Agnostic Meta Learning
Jiang, Y., Konečný, J., Rush, K., & Kannan, S. (2019) · arXiv · doi:10.48550/arxiv.1909.12488 · Cited by 381 · 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…”
MethodSMASH: One-Shot Model Architecture Search through HyperNetworks
Brock, A., Lim, T., Ritchie, J. M., & Weston, N. J. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1708.05344 · Cited by 351 · cited 1×
“Hypernetworks have been widely used in various machine learning applications, such as language modeling [35,40], computer vision [17,19,27], 3D scene representation [28, 38], hyperparameter optimization [2, 25, 29, 31], neural architecture search (NAS) [3, 50], continual learning [44] and meta-learning [55].”
MethodFedBN: Federated Learning on Non-IID Features via Local Batch Normalization
Li, X., Jiang, M., Zhang, X., Kamp, M., & Dou, Q. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2102.07623 · Cited by 332
Adaptive Personalized Federated Learning
Deng, Y., Kamani, M. M., & Mahdavi, M. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.13461 · Cited by 310 · 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…”
MethodThree Approaches for Personalization with Applications to Federated Learning
Mansour, Y., Mohri, M., Ro, J. H., & Suresh, A. T. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.10619 · Cited by 301 · cited 2×
“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…”
BackgroundMethodImplicit Neural Representations with Periodic Activation Functions
Sitzmann, V., Martel, J., Bergman, A. W., Lindell, D. B., & Wetzstein, G. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.09661 · Cited by 261 · cited 1×
“Hypernetworks have been widely used in various machine learning applications, such as language modeling [35,40], computer vision [17,19,27], 3D scene representation [28, 38], hyperparameter optimization [2, 25, 29, 31], neural architecture search (NAS) [3, 50], continual learning [44] and meta-learning [55].”
MethodHyperSeg: Patch-wise Hypernetwork for Real-time Semantic Segmentation
Nirkin, Y., Wolf, L., & Hassner, T. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00405 · Cited by 254
Towards Fair and Privacy-Preserving Federated Deep Models
Lyu, L., Yu, J., Nandakumar, K., Li, Y., Ma, X., Jin, J., Yu, H., & Ng, K. S. (2020) · IEEE Transactions on Parallel and Distributed Systems · doi:10.1109/tpds.2020.2996273 · Cited by 250
Self-citationGraph HyperNetworks for Neural Architecture SearchPreprint
Zhang, C., Ren, M., & Urtasun, R. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1810.05749 · Cited by 233 · cited 1×
“Hypernetworks have been widely used in various machine learning applications, such as language modeling [35,40], computer vision [17,19,27], 3D scene representation [28, 38], hyperparameter optimization [2, 25, 29, 31], neural architecture search (NAS) [3, 50], continual learning [44] and meta-learning [55].”
MethodFederated Learning of a Mixture of Global and Local Models
Hanzely, F., & Richtárik, P. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.05516 · Cited by 230 · 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…”
MethodDitto: Fair and Robust Federated Learning Through Personalization
Li, T., Hu, S., Beirami, A., & Smith, V. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.04221 · Cited by 205 · cited 2×
“To deal with such statistical diversity, personalized federated learning (pFL) mechanisms are proposed to allow each client to train a customized model to adapt to their own data distribution [9, 12, 15, 22].”
BackgroundFederated Evaluation of On-device Personalization
Wang, K., Mathews, R., Kiddon, C., Eichner, H., Beaufays, F., & Ramage, D. (2019) · arXiv · doi:10.48550/arxiv.1910.10252 · Cited by 184
An improved deep learning approach for detection of thyroid papillary cancer in ultrasound images
Li, H., Weng, J., Shi, Y., Gu, W., Mao, Y., Wang, Y., Liu, W., & Zhang, J. (2018) · Scientific Reports · doi:10.1038/s41598-018-25005-7 · Cited by 171
Self-citationDHP: Differentiable Meta Pruning via HyperNetworks
Li, Y., Gu, S., Zhang, K., Gool, L. V., & Timofte, R. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58598-3_36 · Cited by 164
Adaptive Federated Learning on Non-IID Data With Resource Constraint
Zhang, J., Guo, S., Qu, Z., Zeng, D., Zhan, Y., Liu, Q., & Akerkar, R. A. (2021) · IEEE Transactions on Computers · doi:10.1109/tc.2021.3099723 · Cited by 163 · cited 1×
“Federated learning (FL) has emerged as a prominent collaborative machine learning framework to exploit inter-user similarities without sharing the private data [33, 43, 52].”
BackgroundSelf-citationLayer-Wise Adaptive Model Aggregation for Scalable Federated Learning
Lee, S., Zhang, T., & Avestimehr, A. S. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i7.26023 · Cited by 129
Hypernetwork Functional Image Representation
Klocek, S., Maziarka, Ł., Wołczyk, M., Tabor, J., Nowak, J., & Śmieja, M. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-30493-5_48 · Cited by 121
A Beamforming Method Based on Polarization Matching
Yang, X., Gu, J., Jiang, J., & Li, Y. (2020) · 2020 12th International Conference on Advanced Infocomm Technology (ICAIT) · doi:10.1109/icait51223.2020.9315404 · Cited by 107
Deep Meta Functionals for Shape Representation
Littwin, G., & Wolf, L. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00191 · Cited by 105 · cited 1×
“Hypernetworks have been widely used in various machine learning applications, such as language modeling [35,40], computer vision [17,19,27], 3D scene representation [28, 38], hyperparameter optimization [2, 25, 29, 31], neural architecture search (NAS) [3, 50], continual learning [44] and meta-learning [55].”
MethodHa, D., Dai, A., & Le, Q. V. (2016) · arXiv · doi:10.48550/arxiv.1609.09106 · Cited by 100
Federated User Representation LearningPreprint
Bui, D., Malik, K., Goetz, J., Liu, H., Moon, S., Kumar, A., & Shin, K. G. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.12535 · Cited by 86 · 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…”
MethodLower Bounds and Optimal Algorithms for Personalized Federated Learning
Hanzely, F., Hanzely, S., Horváth, S., & Richtárik, P. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.02372 · Cited by 83 · cited 2×
“To deal with such statistical diversity, personalized federated learning (pFL) mechanisms are proposed to allow each client to train a customized model to adapt to their own data distribution [9, 12, 15, 22].”
BackgroundMethodXu, R., Tao, Y., Lu, Z., & Zhong, Y. (2018) · Remote Sensing · doi:10.3390/rs10101602 · Cited by 82
Stochastic Hyperparameter Optimization through Hypernetworks
Lorraine, J., & Duvenaud, D. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1802.09419 · Cited by 76
Meta-Learning via Hypernetworks
Zhao, D., Kobayashi, S., Sacramento, J., & von Oswald, J. (2020) · Repository for Publications and Research Data (ETH Zurich) · doi:10.3929/ethz-b-000465883 · Cited by 71 · cited 1×
“Hypernetworks have been widely used in various machine learning applications, such as language modeling [35,40], computer vision [17,19,27], 3D scene representation [28, 38], hyperparameter optimization [2, 25, 29, 31], neural architecture search (NAS) [3, 50], continual learning [44] and meta-learning [55].”
MethodChirping up the Right Tree: Incorporating Biological Taxonomies into Deep Bioacoustic Classifiers
Cramer, A. L., Lostanlen, V., Farnsworth, A., Salamon, J., & Bello, J. P. (2020) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp40776.2020.9052908 · Cited by 57 · cited 1×
“, the shallow layers focus more on local feature extraction, while the deeper layers are for extracting global features [6, 20, 21, 47, 49].”
BackgroundOn Infinite-Width HypernetworksPreprint
Littwin, E., Galanti, T., Wolf, L., & Yang, G. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.12193 · Cited by 30
Language Modeling with Recurrent Highway Hypernetworks
Suárez, J. (2017) · neural information processing systems · Cited by 19
Delta-STN: Efficient Bilevel Optimization for Neural Networks using Structured Response JacobiansPreprint
Bae, J., & Grosse, R. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.13514 · Cited by 12 · cited 1×
“Hypernetworks have been widely used in various machine learning applications, such as language modeling [35,40], computer vision [17,19,27], 3D scene representation [28, 38], hyperparameter optimization [2, 25, 29, 31], neural architecture search (NAS) [3, 50], continual learning [44] and meta-learning [55].”
Method
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.