启发式ML推理的验证、修复和精化
On Validating, Repairing and Refining Heuristic ML Explanations
摘要:
近年来,人们对机器学习(ML)模型预测的计算解释的兴趣迅速增长。对于不可解释的ML模型,最常用的计算解释方法本质上是启发式的。相比之下,最近的工作提出了计算解释的严格方法,适用于给定的ML模型和整个实例空间的预测。本文将早期的工作扩展到提升树的情况下,并评估与国家的最先进的启发式方法获得的解释的质量。在大多数考虑的数据集,并为绝大多数的情况下,与启发式方法得到的解释被证明是不够的,当整个实例空间(隐式)考虑。
英文摘要:
Recent years have witnessed a fast-growing interest in computing explanations for Machine Learning (ML) models predictions. For non-interpretable ML models, the most commonly used approaches for computing explanations are heuristic in nature. In contrast, recent work proposed rigorous approaches for computing explanations, which hold for a given ML model and prediction over the entire instance space. This paper extends earlier work to the case of boosted trees and assesses the quality of explanations obtained with state-of-the-art heuristic approaches. On most of the datasets considered, and for the vast majority of instances, the explanations obtained with heuristic approaches are shown to be inadequate when the entire instance space is (implicitly) considered.
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。