FLAG: Fast Label-Adaptive Aggregation for Multi-label Classification in Federated Learning

TL;DR

This paper introduces FLAG, a fast label-adaptive aggregation method for multi-label federated learning, which significantly reduces training epochs and communication rounds compared to existing methods.

Contribution

The study proposes a novel multi-label federated learning framework with CMDA and FLAG, addressing the limitations of previous methods that ignored multi-label data characteristics.

Findings

FLAG surpasses state-of-the-art methods in fewer than 50% of training epochs.

The framework effectively handles multi-label data in federated settings.

Experimental results validate the efficiency and effectiveness of the proposed methods.

Abstract

Federated learning aims to share private data to maximize the data utility without privacy leakage. Previous federated learning research mainly focuses on multi-class classification problems. However, multi-label classification is a crucial research problem close to real-world data properties. Nevertheless, a limited number of federated learning studies explore this research problem. Existing studies of multi-label federated learning did not consider the characteristics of multi-label data, i.e., they used the concept of multi-class classification to verify their methods' performance, which means it will not be feasible to apply their methods to real-world applications. Therefore, this study proposed a new multi-label federated learning framework with a Clustering-based Multi-label Data Allocation (CMDA) and a novel aggregation method, Fast Label-Adaptive Aggregation (FLAG), for multi-label classification in the federated learning environment. The experimental results demonstrate that our methods only need less than 50\% of training epochs and communication rounds to surpass the performance of state-of-the-art federated learning methods.