局部可解释性评估中的归因问题及其解决方法
The Blame Problem in Evaluating Local Explanations, and How to Tackle it
AI总结：
针对局部解释评估缺乏最优指标导致技术优劣难辨的问题，提出新评估分类体系，指出多数方法存在归因问题，基于可解释模型真实标签的方法更合理但仍有局限，明确该领域仍为开放研究方向。
摘要：
近年来，局部模型无关解释技术的数量增长迅速。主要原因之一是，由于缺乏最优评估指标，开发新型可解释性技术的门槛较低。没有严谨的评估手段，就很难有确凿证据证明新型解释技术是否能显著优于现有技术。本研究提出了一种评估局部解释的新分类体系：鲁棒性、基于合成数据集与可解释模型的真实标签（ground truth）的评估、模型随机化，以及基于人类认知的评估。通过该分类体系，我们发现除基于可解释模型真实标签的方法外，所有类别的评估方法都存在我们称之为“归因问题（blame problem）”的缺陷。研究指出，这类基于可解释模型真实标签的评估指标是评估局部模型无关解释更合理的方法，但我们也证明即使这类评估指标仍存在进一步的局限性。局部解释的评估仍是一个开放的研究问题。
英文摘要：
The number of local model-agnostic explanation techniques proposed has grown rapidly recently. One main reason is that the bar for developing new explainability techniques is low due to the lack of optimal evaluation measures. Without rigorous measures, it is hard to have concrete evidence of whether the new explanation techniques can significantly outperform their predecessors. Our study proposes a new taxonomy for evaluating local explanations: robustness, evaluation using ground truth from synthetic datasets and interpretable models, model randomization, and human-grounded evaluation. Using this proposed taxonomy, we highlight that all categories of evaluation methods, except those based on the ground truth from interpretable models, suffer from a problem we call the "blame problem." In our study, we argue that this category of evaluation measure is a more reasonable method for evaluating local model-agnostic explanations. However, we show that even this category of evaluation measures has further limitations. The evaluation of local explanations remains an open research problem.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
