CD$^2$-pFed: Cyclic Distillation-guided Channel Decoupling for Model Personalization in Federated Learning

• URL: http://arxiv.org/abs/2204.03880v1
• Date: Fri, 8 Apr 2022 07:13:30 GMT
• Title: CD$^2$-pFed: Cyclic Distillation-guided Channel Decoupling for Model Personalization in Federated Learning
• Authors: Yiqing Shen, Yuyin Zhou, Lequan Yu
• Abstract summary: Federated learning (FL) is a distributed learning paradigm that enables multiple clients to collaboratively learn a shared global model. We propose CD2-pFed, a novel Cyclic Distillation-guided Channel Decoupling framework, to personalize the global model in FL.
• Score: 24.08509828106899
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Federated learning (FL) is a distributed learning paradigm that enables multiple clients to collaboratively learn a shared global model. Despite the recent progress, it remains challenging to deal with heterogeneous data clients, as the discrepant data distributions usually prevent the global model from delivering good generalization ability on each participating client. In this paper, we propose CD^2-pFed, a novel Cyclic Distillation-guided Channel Decoupling framework, to personalize the global model in FL, under various settings of data heterogeneity. Different from previous works which establish layer-wise personalization to overcome the non-IID data across different clients, we make the first attempt at channel-wise assignment for model personalization, referred to as channel decoupling. To further facilitate the collaboration between private and shared weights, we propose a novel cyclic distillation scheme to impose a consistent regularization between the local and global model representations during the federation. Guided by the cyclical distillation, our channel decoupling framework can deliver more accurate and generalized results for different kinds of heterogeneity, such as feature skew, label distribution skew, and concept shift. Comprehensive experiments on four benchmarks, including natural image and medical image analysis tasks, demonstrate the consistent effectiveness of our method on both local and external validations.

Related papers

• Overcoming Data and Model Heterogeneities in Decentralized Federated Learning via Synthetic Anchors [21.931436901703634]
  Conventional Federated Learning (FL) involves collaborative training of a global model while maintaining user data privacy. One of its branches, decentralized FL, is a serverless network that allows clients to own and optimize different local models separately. We propose a novel Decentralized FL technique by introducing Synthetic Anchors, dubbed as DeSA.
  arXiv  Detail & Related papers  (2024-05-19T11:36:45Z)
• An Aggregation-Free Federated Learning for Tackling Data Heterogeneity [50.44021981013037]
  Federated Learning (FL) relies on the effectiveness of utilizing knowledge from distributed datasets. Traditional FL methods adopt an aggregate-then-adapt framework, where clients update local models based on a global model aggregated by the server from the previous training round. We introduce FedAF, a novel aggregation-free FL algorithm.
  arXiv  Detail & Related papers  (2024-04-29T05:55:23Z)
• FedImpro: Measuring and Improving Client Update in Federated Learning [77.68805026788836]
  Federated Learning (FL) models often experience client drift caused by heterogeneous data. We present an alternative perspective on client drift and aim to mitigate it by generating improved local models.
  arXiv  Detail & Related papers  (2024-02-10T18:14:57Z)
• Spectral Co-Distillation for Personalized Federated Learning [69.97016362754319]
  We propose a novel distillation method based on model spectrum information to better capture generic versus personalized representations. We also introduce a co-distillation framework that establishes a two-way bridge between generic and personalized model training. We demonstrate the outperformance and efficacy of our proposed spectral co-distillation method, as well as our wait-free training protocol.
  arXiv  Detail & Related papers  (2024-01-29T16:01:38Z)
• Federated Learning with Projected Trajectory Regularization [65.6266768678291]
  Federated learning enables joint training of machine learning models from distributed clients without sharing their local data. One key challenge in federated learning is to handle non-identically distributed data across the clients. We propose a novel federated learning framework with projected trajectory regularization (FedPTR) for tackling the data issue.
  arXiv  Detail & Related papers  (2023-12-22T02:12:08Z)
• Fed-CO2: Cooperation of Online and Offline Models for Severe Data Heterogeneity in Federated Learning [14.914477928398133]
  Federated Learning (FL) has emerged as a promising distributed learning paradigm. The effectiveness of FL is highly dependent on the quality of the data that is being used for training. We propose Fed-CO$_2$, a universal FL framework that handles both label distribution skew and feature skew.
  arXiv  Detail & Related papers  (2023-12-21T15:12:12Z)
• Heterogeneous Federated Learning via Personalized Generative Networks [7.629157720712401]
  Federated Learning (FL) allows several clients to construct a common global machine-learning model without having to share their data. We propose a method for knowledge transfer between clients where the server trains client-specific generators.
  arXiv  Detail & Related papers  (2023-08-25T09:37:02Z)
• PFL-GAN: When Client Heterogeneity Meets Generative Models in Personalized Federated Learning [55.930403371398114]
  We propose a novel generative adversarial network (GAN) sharing and aggregation strategy for personalized learning (PFL) PFL-GAN addresses the client heterogeneity in different scenarios. More specially, we first learn the similarity among clients and then develop an weighted collaborative data aggregation. The empirical results through the rigorous experimentation on several well-known datasets demonstrate the effectiveness of PFL-GAN.
  arXiv  Detail & Related papers  (2023-08-23T22:38:35Z)
• DRFLM: Distributionally Robust Federated Learning with Inter-client Noise via Local Mixup [58.894901088797376]
  federated learning has emerged as a promising approach for training a global model using data from multiple organizations without leaking their raw data. We propose a general framework to solve the above two challenges simultaneously. We provide comprehensive theoretical analysis including robustness analysis, convergence analysis, and generalization ability.
  arXiv  Detail & Related papers  (2022-04-16T08:08:29Z)
• Adapt to Adaptation: Learning Personalization for Cross-Silo Federated Learning [6.0088002781256185]
  Conventional federated learning aims to train a global model for a federation of clients with decentralized data. The distribution shift across non-IID datasets, also known as the data heterogeneity, often poses a challenge for this one-global-model-fits-all solution. We propose APPLE, a personalized cross-silo FL framework that adaptively learns how much each client can benefit from other clients' models.
  arXiv  Detail & Related papers  (2021-10-15T22:23:14Z)
• Personalized Federated Learning by Structured and Unstructured Pruning under Data Heterogeneity [3.291862617649511]
  We propose a new approach for obtaining a personalized model from a client-level objective. To realize this personalization, we leverage finding a small subnetwork for each client.
  arXiv  Detail & Related papers  (2021-05-02T22:10:46Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.