Visual Prompt Based Personalized Federated Learning
Abstract: As a popular paradigm of distributed learning, personalized federated learning (PFL) allows personalized models to improve generalization ability and robustness by utilizing knowledge from all distributed clients. Most existing PFL algorithms tackle personalization in a model-centric way, such as personalized layer partition, model regularization, and model interpolation, which all fail to take into account the data characteristics of distributed clients. In this paper, we propose a novel PFL framework for image classification tasks, dubbed pFedPT, that leverages personalized visual prompts to implicitly represent local data distribution information of clients and provides that information to the aggregation model to help with classification tasks. Specifically, in each round of pFedPT training, each client generates a local personalized prompt related to local data distribution. Then, the local model is trained on the input composed of raw data and a visual prompt to learn the distribution information contained in the prompt. During model testing, the aggregated model obtains client-specific knowledge of the data distributions based on the prompts, which can be seen as an adaptive fine-tuning of the aggregation model to improve model performances on different clients. Furthermore, the visual prompt can be added as an orthogonal method to implement personalization on the client for existing FL methods to boost their performance. Experiments on the CIFAR10 and CIFAR100 datasets show that pFedPT outperforms several state-of-the-art (SOTA) PFL algorithms by a large margin in various settings. The code is available at: https://github.com/hkgdifyu/pFedPT.
Submission Length: Long submission (more than 12 pages of main content)
Changes Since Last Submission: 1. Change all previous red markings to black.
2. Add a link to the public code repository for the algorithm in the abstract section.
3. Examine the effectiveness of soft visual prompts for pFedPT in Non-IID scenarios and experimental results and related discussions are presented in Tab. 6 of the appendix.
Video: https://youtu.be/kzBMpZ7od1k
Code: https://github.com/hkgdifyu/pFedPT
Assigned Action Editor: ~Kui_Jia1
License: Creative Commons Attribution 4.0 International (CC BY 4.0)
Submission Number: 1532
Loading