What type of study is this?

This is a Experimental Study study.

October 5, 2025Open Access

EVO-LRP: Evolutionary Optimization of LRP for Interpretable Model Explanations

EZEmerald ZhangThe University of Texas at Austin JWJames WeaverMarion Local Schools SSSamantha R. SantacruzThe University of Texas at Austin

Key Points

EVO-LRP significantly enhances attribution quality through task-specific optimization.
It leverages covariance matrix adaptation evolution strategy to refine hyperparameters effectively.
The method demonstrates improved performance in interpretability metrics compared to traditional methods.
This approach shows strong sensitivity to class-specific features, enhancing model transparency.

Abstract

Explainable AI (XAI) methods help identify which image regions influence a model's prediction, but often face a trade-off between detail and interpretability. Layer-wise Relevance Propagation (LRP) offers a model-aware alternative. However, LRP implementations commonly rely on heuristic rule sets that are not optimized for clarity or alignment with model behavior. We introduce EVO-LRP, a method that applies Covariance Matrix Adaptation Evolution Strategy (CMA-ES) to tune LRP hyperparameters based on quantitative interpretability metrics, such as faithfulness or sparseness. EVO-LRP outperforms traditional XAI approaches in both interpretability metric performance and visual coherence, with strong sensitivity to class-specific features. These findings demonstrate that attribution quality can be systematically improved through principled, task-specific optimization.

Demander à l'IA

Bookmark

View Full Paper