Explainable AI-aided Feature Selection and Model Reduction for DRL-based V2X Resource Allocation

2025-01-23

AI Summary

To address the poor interpretability and high computational overhead of deep reinforcement learning (DRL)-based resource allocation in 6G vehicle-to-everything (V2X) networks, this paper proposes a model-agnostic, two-stage explainable AI (XAI)-driven optimization framework. It innovatively applies SHAP-based feature importance analysis directly to state-space pruning and parameter compression in multi-agent DRL (MADRL), enabling end-to-end lightweight model design. Evaluated on an 8-pair V2X node scenario, the method retains 97% of the original sum-rate performance while reducing critical state features by 28%, training time by 11%, and trainable parameters by 46%. The core contribution lies in pioneering the shift of XAI from post-hoc explanation to proactive model architecture optimization—establishing a novel XAI-driven lightweighting paradigm for MADRL in 6G V2X systems.

Technology Category

• Humans and AI: Explainable AI (XAI) for Human Understanding
• Machine Learning: Hardware-aware ML
• Planning, Routing, and Scheduling: Model-Based Reasoning

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

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.

Problem

• 6G Networks
• Interpretable Artificial Intelligence
• Wireless Resource Allocation

Innovation

• XAI (Explainable Artificial Intelligence)
• Multi-Agent Deep Reinforcement Learning
• 6G Vehicular Communication