Joint Explainability and Sensitivity-Aware Federated Deep Learning for Transparent 6G RAN Slicing

TL;DR

This paper introduces an explainable federated deep learning model for 6G RAN slicing that predicts traffic drops while ensuring model transparency and sensitivity-awareness, validated through simulation.

Contribution

It presents a novel federated learning approach incorporating explainability and sensitivity metrics as constraints for 6G network slicing.

Findings

The proposed model outperforms baseline in traffic prediction accuracy.

Incorporating explainability constraints improves trustworthiness.

Simulation confirms the effectiveness of the approach.

Abstract

In recent years, wireless networks are evolving complex, which upsurges the use of zero-touch artificial intelligence (AI)-driven network automation within the telecommunication industry. In particular, network slicing, the most promising technology beyond 5G, would embrace AI models to manage the complex communication network. Besides, it is also essential to build the trustworthiness of the AI black boxes in actual deployment when AI makes complex resource management and anomaly detection. Inspired by closed-loop automation and Explainable Artificial intelligence (XAI), we design an Explainable Federated deep learning (FDL) model to predict per-slice RAN dropped traffic probability while jointly considering the sensitivity and explainability-aware metrics as constraints in such non-IID setup. In precise, we quantitatively validate the faithfulness of the explanations via the so-called attribution-based \emph{log-odds metric} that is included as a constraint in the run-time FL optimization task. Simulation results confirm its superiority over an unconstrained integrated-gradient (IG) \emph{post-hoc} FDL baseline.