Exploring One-shot Semi-supervised Federated Learning with A Pre-trained Diffusion Model
Recently, semi-supervised federated learning (semi-FL) has been proposed to handle the commonly seen real-world scenarios with labeled data on the server and unlabeled data on the clients. However, existing methods face several challenges such as communication costs, data heterogeneity, and training pressure on client devices. To address these challenges, we introduce the powerful diffusion models (DM) into semi-FL and propose FedDISC, a Federated Diffusion-Inspired Semi-supervised Co-training method. Specifically, we first extract prototypes of the labeled server data and use these prototypes to predict pseudo-labels of the client data. For each category, we compute the cluster centroids and domain-specific representations to signify the semantic and stylistic information of their distributions. After adding noise, these representations are sent back to the server, which uses the pre-trained DM to generate synthetic datasets complying with the client distributions and train a global model on it. With the assistance of vast knowledge within DM, the synthetic datasets have comparable quality and diversity to the client images, subsequently enabling the training of global models that achieve performance equivalent to or even surpassing the ceiling of supervised centralized training. FedDISC works within one communication round, does not require any local training, and involves very minimal information uploading, greatly enhancing its practicality. Extensive experiments on three large-scale datasets demonstrate that FedDISC effectively addresses the semi-FL problem on non-IID clients and outperforms the compared SOTA methods. Sufficient visualization experiments also illustrate that the synthetic dataset generated by FedDISC exhibits comparable diversity and quality to the original client dataset, with a neglectable possibility of leaking privacy-sensitive information of the clients.
Code (0)
등록된 구현이 없습니다.
Tasks
DiversityFederated LearningPrivacy PreservingMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Federated Self-Supervised Learning for One-Shot Cross-Modal and Cross-Imaging Technique Segmentation
Decentralized federated learning enables learning of data representations from multiple sources without compromising the privacy of the clients. In applications like medical image segmentation, where obtaining a large an…
Federated LearningImage SegmentationMedical Image SegmentationOne-Shot Segmentation+3Cross-client Label Propagation for Transductive and Semi-Supervised Federated Learning
We present Cross-Client Label Propagation(XCLP), a new method for transductive federated learning. XCLP estimates a data graph jointly from the data of multiple clients and computes labels for the unlabeled data by propa…
Federated LearningPseudo LabelFederated Semi-supervised Learning for Medical Image Segmentation with intra-client and inter-client Consistency
Medical image segmentation plays a vital role in clinic disease diagnosis and medical image analysis. However, labeling medical images for segmentation task is tough due to the indispensable domain expertise of radiologi…
Data AugmentationFederated LearningImage SegmentationMedical Image Analysis+4FedParsing: a Semi-Supervised Federated Learning Model on Semantic Parsing
Although many semantic parsing models have been proven to work effectively on "NL-to-SQL", the limitation of annotated datasets remains a great challenge. In many semi-supervised models, while they use unlabeled data to …
Federated LearningSemantic ParsingLightweight Unsupervised Federated Learning with Pretrained Vision Language Model
Federated learning aims to tackle the ``isolated data island" problem, where it trains a collective model from physically isolated clients while safeguarding the privacy of users' data. However, supervised federated lear…
Federated LearningLanguage ModelingLanguage Modelling