用进化算法优化LRP，让模型解释更准确清晰。
EVO-LRP: Evolutionary Optimization of LRP for Interpretable Model Explanations
- 用进化策略自动调优LRP参数，提升解释质量
- 在可解释性指标和视觉一致性上优于传统方法
- 适合需要精准归因的模型分析场景
可解释人工智能（XAI）方法有助于识别影响模型预测的图像区域，但常面临细节与可读性之间的权衡。层间相关性传播（LRP）提供了一种基于模型的替代方案。然而，现有LRP实现多依赖于未优化的启发式规则，难以保证解释的清晰度或与模型行为的一致性。本文提出EVO-LRP，采用协方差矩阵自适应进化策略（CMA-ES）根据可解释性量化指标（如忠实度、稀疏性）优化LRP超参数。实验表明，EVO-LRP在可解释性指标表现和视觉连贯性上均优于传统XAI方法，对特定类别特征具有强敏感性。结果表明，通过任务定制的系统性优化，可显著提升归因质量。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。