理解事后解释器：以Anchors为例
Understanding Post-hoc Explainers: The Case of Anchors
AI总结：
针对机器学习可解释性方法缺乏理论保障的问题，对基于规则的解释方法Anchors开展理论分析，形式化其算法并证明其搭配TF-IDF向量化线性文本分类器时结果有效，为可解释性方法开发提供理论支撑框架。
摘要：
在许多场景中，机器学习模型的可解释性是一项高度必要却难以实现的任务。为解释这类模型的单个预测结果，研究者已提出局部模型无关方法。然而，对用户而言，生成解释的过程可能和待解释的预测一样难以理解。此外，可解释性方法往往缺乏理论保障，它们在简单模型上的表现通常也不明确。尽管要确保解释器在前沿模型上按预期运行即便并非不可能，也十分困难，但我们至少可以确保其在简单的、本身具备可解释性的模型上正常运作。本文对Anchors（Ribeiro等人，2018）展开理论分析，这是一种流行的基于规则的可解释性方法，通过高亮少量单词来解释文本分类器的决策。在形式化其算法并提供实用见解后，我们通过数学证明，当Anchors与基于TF-IDF向量化的线性文本分类器搭配使用时，会产生有意义的结果。我们认为，本研究的分析框架可助力开发基于坚实理论基础的新型可解释性方法。
英文摘要：
In many scenarios, the interpretability of machine learning models is a highly required but difficult task. To explain the individual predictions of such models, local model-agnostic approaches have been proposed. However, the process generating the explanations can be, for a user, as mysterious as the prediction to be explained. Furthermore, interpretability methods frequently lack theoretical guarantees, and their behavior on simple models is frequently unknown. While it is difficult, if not impossible, to ensure that an explainer behaves as expected on a cutting-edge model, we can at least ensure that everything works on simple, already interpretable models. In this paper, we present a theoretical analysis of Anchors (Ribeiro et al., 2018): a popular rule-based interpretability method that highlights a small set of words to explain a text classifier's decision. After formalizing its algorithm and providing useful insights, we demonstrate mathematically that Anchors produces meaningful results when used with linear text classifiers on top of a TF-IDF vectorization. We believe that our analysis framework can aid in the development of new explainability methods based on solid theoretical foundations.
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。
