arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2109.07804cs.LGcs.CV
收藏

评价单元组成偏差的检测精度

Detection Accuracy for Evaluating Compositional Explanations of Units

Sapienza University of Rome(罗马大学);Sony AI(索尼人工智能)

Sayo M. Makinwa, Biagio La Rosa, Roberto Capobianco

摘要:

最近深度学习模型在解决复杂问题和不同领域的成功增加了人们对理解它们所学到的东西的兴趣。因此,不同的方法被用来解释这些模型,其中之一是使用人类可理解的概念作为解释。使用这种方法的两个例子是网络剖析和组合解释。前者使用原子概念解释单位,而后者使解释更具表现力,用逻辑形式取代原子概念。虽然直观上,逻辑形式比原子概念更能提供信息,但如何量化这种改进并不清楚,并且它们的评估通常基于在搜索过程中优化的相同度量以及待调优的超参数的使用。在本文中,我们建议使用检测准确度作为评估指标,它衡量单元对其指定解释的检测一致性。我们表明,该度量(1)有效地评估不同长度的解释,(2)可以用作组合解释搜索的停止标准,消除解释长度超参数,(3)暴露新的专门化单元,其长度为1的解释是其较长解释的感知抽象。

英文摘要:

The recent success of deep learning models in solving complex problems and in different domains has increased interest in understanding what they learn. Therefore, different approaches have been employed to explain these models, one of which uses human-understandable concepts as explanations. Two examples of methods that use this approach are Network Dissection and Compositional explanations. The former explains units using atomic concepts, while the latter makes explanations more expressive, replacing atomic concepts with logical forms. While intuitively, logical forms are more informative than atomic concepts, it is not clear how to quantify this improvement, and their evaluation is often based on the same metric that is optimized during the search-process and on the usage of hyper-parameters to be tuned. In this paper, we propose to use as evaluation metric the Detection Accuracy, which measures units' consistency of detection of their assigned explanations. We show that this metric (1) evaluates explanations of different lengths effectively, (2) can be used as a stopping criterion for the compositional explanation search, eliminating the explanation length hyper-parameter, and (3) exposes new specialized units whose length 1 explanations are the perceptual abstractions of their longer explanations.

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。

↑