提出新评估指标EAI，解决解释性AI中特征重要性评价的偏差问题
Re-Visiting Explainable AI Evaluation Metrics to Identify The Most Informative Features
- 引入预期准确率区间EAI，预测特征移除或打乱后的模型性能上下界
- 实验证明传统指标ROAR和PI在共线性下表现不可靠，易误判特征重要性
- 特别适合高共线性数据，为解释性AI评估提供更稳健的量化工具
功能型或代理型方法是评估可解释人工智能（XAI）质量的常用方式，通过统计方法、定义及新开发的指标进行无须人工干预的评估。其中，选择性（或移除并重训，ROAR）和置换重要性（PI）是最常用于识别机器学习模型中关键特征的指标。它们认为：若移除或打乱最显著特征，模型性能应明显下降。然而，这两项指标的效能受多重共线性、模型中显著特征数量及模型准确性的影响显著。本文通过实证案例表明，两种指标均存在上述局限性。为此，我们提出预期准确率区间（EAI），用于预测在实施ROAR或PI时模型准确率的上下界。该指标在共线性特征场景下表现出极强实用性。
原文摘要 · Abstract (English)
Functionality or proxy-based approach is one of the used approaches to evaluate the quality of explainable artificial intelligence methods. It uses statistical methods, definitions and new developed metrics for the evaluation without human intervention. Among them, Selectivity or RemOve And Retrain (ROAR), and Permutation Importance (PI) are the most commonly used metrics to evaluate the quality of explainable artificial intelligence methods to highlight the most significant features in machine learning models. They state that the model performance should experience a sharp reduction if the most informative feature is removed from the model or permuted. However, the efficiency of both metrics is significantly affected by multicollinearity, number of significant features in the model and the accuracy of the model. This paper shows with empirical examples that both metrics suffer from the aforementioned limitations. Accordingly, we propose expected accuracy interval (EAI), a metric to predict the upper and lower bounds of the the accuracy of the model when ROAR or IP is implemented. The proposed metric found to be very useful especially with collinear features.
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。