Work

Federated Active Learning (F-AL): An Efficient Annotation Strategy for Federated Learning

Year: 2024

Type: article

Abstract: Federated learning (FL) has been intensively investigated in terms of communication efficiency, privacy, and fairness. However, efficient annotation, which is a pain point in real-world FL applications, is less studied. In this project, we propose to apply active learning (AL) to the FL framework to reduce the annotation workload. We expect that the AL and FL can improve the performance of each other complementarily. In our proposed federated active learning (F-AL) method, the clients collaboratively execute the AL to obtain the instances which are considered informative to FL in a distributed optimization manner. We compare the test accuracies of the global FL models using the conventional random sampling strategy, client-level separate AL (S-AL), and the proposed F-AL. We empirically demonstrate that the F-AL outperforms baseline methods in image classification tasks.

Source: IEEE Access

DOI: 10.1109/access.2024.3376746

Authors: Jin-Hyun Ahn, Yeeun Ma, Seoyun Park, Cheolwoo You

Institution: Myongji University

Language: English

Topic: Privacy-Preserving Technologies in Data

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: gold

Estimated APC paid: $1,995

Funders: National Research Foundation, Myongji University, National Research Foundation of Korea, Ministry of Science and ICT, South Korea