arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.03103cs.LG
收藏

从特征交互的视角看可解释的人工智能

Interpretable Artificial Intelligence through the Lens of Feature Interaction

University of Southern California(南加利福尼亚大学)

Michael Tsang, James Enouen, Yan Liu

摘要:

深度学习模型的解释是一个非常具有挑战性的问题,因为它们有大量的参数,节点之间的复杂连接以及难以理解的特征表示。尽管如此,许多人认为可解释性是可信度、公平性和安全性的关键解决方案,特别是当深度学习被应用于更关键的决策任务时,如信贷审批、工作筛选和累犯预测。有大量优秀的研究为深度学习模型提供了可解释性;然而,许多常用的方法没有考虑一种称为“特征交互”的现象。“这项工作首先解释了特征交互的历史和现代重要性,然后调查了明确考虑特征交互的现代可解释性方法。本调查旨在揭示特征交互在机器学习可解释性的更大背景下的重要性,特别是在深度学习模型严重依赖特征交互的现代背景下。

英文摘要:

Interpretation of deep learning models is a very challenging problem because of their large number of parameters, complex connections between nodes, and unintelligible feature representations. Despite this, many view interpretability as a key solution to trustworthiness, fairness, and safety, especially as deep learning is applied to more critical decision tasks like credit approval, job screening, and recidivism prediction. There is an abundance of good research providing interpretability to deep learning models; however, many of the commonly used methods do not consider a phenomenon called "feature interaction." This work first explains the historical and modern importance of feature interactions and then surveys the modern interpretability methods which do explicitly consider feature interactions. This survey aims to bring to light the importance of feature interactions in the larger context of machine learning interpretability, especially in a modern context where deep learning models heavily rely on feature interactions.

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。

↑