A New Perspective on Privacy Protection in Federated Learning with Granular-Ball Computing

TL;DR

This paper introduces Granular-Ball Federated Learning (GrBFL), a novel privacy-preserving framework that segments images into coarse regions for efficient, secure, and effective federated image classification.

Contribution

It proposes a new input-level privacy approach using image segmentation into coarse regions and graph reconstruction, improving privacy and efficiency in federated learning.

Findings

Outperforms state-of-the-art FL methods in accuracy and efficiency

Effectively preserves privacy by coarse image segmentation

Enhances model utility while reducing redundant information

Abstract

Federated Learning (FL) facilitates collaborative model training while prioritizing privacy by avoiding direct data sharing. However, most existing articles attempt to address challenges within the model's internal parameters and corresponding outputs, while neglecting to solve them at the input level. To address this gap, we propose a novel framework called Granular-Ball Federated Learning (GrBFL) for image classification. GrBFL diverges from traditional methods that rely on the finest-grained input data. Instead, it segments images into multiple regions with optimal coarse granularity, which are then reconstructed into a graph structure. We designed a two-dimensional binary search segmentation algorithm based on variance constraints for GrBFL, which effectively removes redundant information while preserving key representative features. Extensive theoretical analysis and experiments demonstrate that GrBFL not only safeguards privacy and enhances efficiency but also maintains robust utility, consistently outperforming other state-of-the-art FL methods. The code is available at https://github.com/AIGNLAI/GrBFL.