paper-with-me

홈 › Papers

FedIL: Federated Incremental Learning from Decentralized Unlabeled Data with Convergence Analysis

2023-02-23 · Nan Yang, Dong Yuan, Charles Z Liu, Yongkun Deng, Wei Bao

Most existing federated learning methods assume that clients have fully labeled data to train on, while in reality, it is hard for the clients to get task-specific labels due to users' privacy concerns, high labeling costs, or lack of expertise. This work considers the server with a small labeled dataset and intends to use unlabeled data in multiple clients for semi-supervised learning. We propose a new framework with a generalized model, Federated Incremental Learning (FedIL), to address the problem of how to utilize labeled data in the server and unlabeled data in clients separately in the scenario of Federated Learning (FL). FedIL uses the Iterative Similarity Fusion to enforce the server-client consistency on the predictions of unlabeled data and uses incremental confidence to establish a credible pseudo-label set in each client. We show that FedIL will accelerate model convergence by Cosine Similarity with normalization, proved by Banach Fixed Point Theorem. The code is available at https://anonymous.4open.science/r/fedil.

📄 PDF Abstract BibTeX arXiv:2302.11823

Code (0)

등록된 구현이 없습니다.

Tasks

Federated LearningIncremental LearningPseudo Label

Similar Papers 제목 키워드 기반

FediLoRA: Practical Federated Fine-Tuning of Foundation Models Under Missing-Modality Constraints

2025-09-01 · Lishan Yang, Wei Emma Zhang, Nam Kha Nguygen, Po Hu 외 arxiv

Federated Learning with LoRA fine-tuning offers an efficient and privacy-aware solution for institutions to collaboratively leverage their large datasets to train VLLMs. However, participating institutions often possess …

Federated Learning

FedILC: Weighted Geometric Mean and Invariant Gradient Covariance for Federated Learning on Non-IID Data

2022-05-19 · Mike He Zhu, Léna Néhale Ezzine, Dianbo Liu, Yoshua Bengio

Federated learning is a distributed machine learning approach which enables a shared server model to learn by aggregating the locally-computed parameter updates with the training data from spatially-distributed client si…

Federated Learning

Decentralized Federated Dataset Dictionary Learning for Multi-Source Domain Adaptation

2025-03-22 · Rebecca Clain, Eduardo Fernandes Montesuma, Fred Ngolè Mboula

Decentralized Multi-Source Domain Adaptation (DMSDA) is a challenging task that aims to transfer knowledge from multiple related and heterogeneous source domains to an unlabeled target domain within a decentralized frame…

Dictionary LearningDomain Adaptation

Federated Contrastive Learning for Decentralized Unlabeled Medical Images

2021-09-15 · Nanqing Dong, Irina Voiculescu

A label-efficient paradigm in computer vision is based on self-supervised contrastive pre-training on unlabeled data followed by fine-tuning with a small number of labels. Making practical use of a federated computing en…

Contrastive LearningData AugmentationFederated Learning

FedSR: A Semi-Decentralized Federated Learning Algorithm for Non-IIDness in IoT System

2024-03-19 · Jianjun Huang, Lixin Ye, Li Kang

In the Industrial Internet of Things (IoT), a large amount of data will be generated every day. Due to privacy and security issues, it is difficult to collect all these data together to train deep learning models, thus t…

Federated Learning