研究概念激活向量的随机性，发现其方差随样本量呈1/N下降。
On The Variability of Concept Activation Vectors
- 通过理论分析量化概念激活向量的随机波动
- 实验证明方差与采样数量成反比，比例系数为1/N
- 给出高效使用该方法的实用建议，节省计算资源
人工智能透明化是当前重大挑战之一。可解释人工智能中，基于概念的解释方法（如概念激活向量，CAVs）成为重要方向。然而，CAVs的构建依赖于从训练集随机采样，导致不同用户得到的向量存在差异。本文对CAVs构造过程进行细粒度理论分析，量化其变异性。实验在多个真实数据集上验证，结果表明：CAVs的方差随采样数量N呈1/N下降。基于此，我们提出资源高效的使用建议。
原文摘要 · Abstract (English)
One of the most pressing challenges in artificial intelligence is to make models more transparent to their users. Recently, explainable artificial intelligence has come up with numerous method to tackle this challenge. A promising avenue is to use concept-based explanations, that is, high-level concepts instead of plain feature importance score. Among this class of methods, Concept Activation vectors (CAVs), Kim et al. (2018) stands out as one of the main protagonists. One interesting aspect of CAVs is that their computation requires sampling random examples in the train set. Therefore, the actual vectors obtained may vary from user to user depending on the randomness of this sampling. In this paper, we propose a fine-grained theoretical analysis of CAVs construction in order to quantify their variability. Our results, confirmed by experiments on several real-life datasets, point out towards an universal result: the variance of CAVs decreases as $1/N$, where $N$ is the number of random examples. Based on this we give practical recommendations for a resource-efficient application of the method.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。