Explanation-Guided Fair Federated Learning for Transparent 6G RAN Slicing

TL;DR

This paper introduces an explanation-guided federated learning scheme for 6G RAN slicing that enhances transparency, fairness, and trustworthiness of AI models by leveraging explainability metrics during training.

Contribution

It proposes a novel explanation-guided federated learning approach using Jensen-Shannon divergence to improve model faithfulness and fairness in 6G network automation.

Findings

Over 50% increase in comprehensiveness score compared to baselines.

More than 25% improvement in recall score over unconstrained models.

Enhanced trustworthiness and fairness in AI predictions for 6G RAN slicing.

Abstract

Future zero-touch artificial intelligence (AI)-driven 6G network automation requires building trust in the AI black boxes via explainable artificial intelligence (XAI), where it is expected that AI faithfulness would be a quantifiable service-level agreement (SLA) metric along with telecommunications key performance indicators (KPIs). This entails exploiting the XAI outputs to generate transparent and unbiased deep neural networks (DNNs). Motivated by closed-loop (CL) automation and explanation-guided learning (EGL), we design an explanation-guided federated learning (EGFL) scheme to ensure trustworthy predictions by exploiting the model explanation emanating from XAI strategies during the training run time via Jensen-Shannon (JS) divergence. Specifically, we predict per-slice RAN dropped traffic probability to exemplify the proposed concept while respecting fairness goals formulated in terms of the recall metric which is included as a constraint in the optimization task. Finally, the comprehensiveness score is adopted to measure and validate the faithfulness of the explanations quantitatively. Simulation results show that the proposed EGFL-JS scheme has achieved more than $50\%$ increase in terms of comprehensiveness compared to different baselines from the literature, especially the variant EGFL-KL that is based on the Kullback-Leibler Divergence. It has also improved the recall score with more than $25\%$ relatively to unconstrained-EGFL.