EVO-LRP: Evolutionary Optimization of LRP for Interpretable Model Explanations
This work addresses the need for more interpretable AI explanations in domains like image analysis, though it is incremental as it builds on existing LRP methods.
The paper tackles the problem of optimizing Layer-wise Relevance Propagation (LRP) hyperparameters for interpretable model explanations by introducing EVO-LRP, which uses evolutionary optimization to improve interpretability metrics and visual coherence, outperforming traditional methods.
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.