Explainable AI-aided Feature Selection and Model Reduction for DRL-based V2X Resource Allocation
This addresses the challenge of implementing complex AI models in practical V2X communications for network operators, though it is incremental as it applies known XAI methods to a specific domain.
The paper tackles the lack of explainability in deep learning models for radio resource management in 6G networks by proposing an explainable AI framework for feature selection and model reduction in multi-agent deep reinforcement learning, achieving 97% of the original sum-rate performance while reducing state features by 28%, training time by 11%, and parameters by 46%.
Artificial intelligence (AI) is expected to significantly enhance radio resource management (RRM) in sixth-generation (6G) networks. However, the lack of explainability in complex deep learning (DL) models poses a challenge for practical implementation. This paper proposes a novel explainable AI (XAI)- based framework for feature selection and model complexity reduction in a model-agnostic manner. Applied to a multi-agent deep reinforcement learning (MADRL) setting, our approach addresses the joint sub-band assignment and power allocation problem in cellular vehicle-to-everything (V2X) communications. We propose a novel two-stage systematic explainability framework leveraging feature relevance-oriented XAI to simplify the DRL agents. While the former stage generates a state feature importance ranking of the trained models using Shapley additive explanations (SHAP)-based importance scores, the latter stage exploits these importance-based rankings to simplify the state space of the agents by removing the least important features from the model input. Simulation results demonstrate that the XAI-assisted methodology achieves 97% of the original MADRL sum-rate performance while reducing optimal state features by 28%, average training time by 11%, and trainable weight parameters by 46% in a network with eight vehicular pairs.