GAI-Enabled Explainable Personalized Federated Semi-Supervised Learning

TL;DR

This paper introduces XPFL, a novel federated learning framework that combines generative AI for semi-supervised learning, personalization, and explainability, addressing real-world challenges like label scarcity and non-IID data.

Contribution

The paper presents GFed for GAI-assisted semi-supervised local training and XFed for explainability, integrating personalization and visualization in federated learning.

Findings

Effective semi-supervised learning with GAI assistance.

Enhanced model explainability via decision trees and t-SNE visualization.

Improved personalization and global model performance in simulations.

Abstract

Federated learning (FL) is a commonly distributed algorithm for mobile users (MUs) training artificial intelligence (AI) models, however, several challenges arise when applying FL to real-world scenarios, such as label scarcity, non-IID data, and unexplainability. As a result, we propose an explainable personalized FL framework, called XPFL. First, we introduce a generative AI (GAI) assisted personalized federated semi-supervised learning, called GFed. Particularly, in local training, we utilize a GAI model to learn from large unlabeled data and apply knowledge distillation-based semi-supervised learning to train the local FL model using the knowledge acquired from the GAI model. In global aggregation, we obtain the new local FL model by fusing the local and global FL models in specific proportions, allowing each local model to incorporate knowledge from others while preserving its personalized characteristics. Second, we propose an explainable AI mechanism for FL, named XFed. Specifically, in local training, we apply a decision tree to match the input and output of the local FL model. In global aggregation, we utilize t-distributed stochastic neighbor embedding (t-SNE) to visualize the local models before and after aggregation. Finally, simulation results validate the effectiveness of the proposed XPFL framework.