[论文解读] Algorithm-Agnostic Explainability for Unsupervised Clustering

Charles A. Ellis, Mohammad S.E. Sendi+4 more|arXiv (Cornell University)|May 17, 2021

Explainable Artificial Intelligence (XAI)参考文献 44被引用 27

一句话总结

本文提出两种全局/局部、算法无关的可解释性方法（G2PC 和 L2PC），用于解释跨多种算法的无监督聚类；在合成数据和高维 fMRI 连接性数据上进行了演示。

ABSTRACT

Supervised machine learning explainability has developed rapidly in recent years. However, clustering explainability has lagged behind. Here, we demonstrate the first adaptation of model-agnostic explainability methods to explain unsupervised clustering. We present two novel "algorithm-agnostic" explainability methods - global permutation percent change (G2PC) and local perturbation percent change (L2PC) - that identify feature importance globally to a clustering algorithm and locally to the clustering of individual samples. The methods are (1) easy to implement and (2) broadly applicable across clustering algorithms, which could make them highly impactful. We demonstrate the utility of the methods for explaining five popular clustering methods on low-dimensional synthetic datasets and on high-dimensional functional network connectivity data extracted from a resting-state functional magnetic resonance imaging dataset of 151 individuals with schizophrenia and 160 controls. Our results are consistent with existing literature while also shedding new light on how changes in brain connectivity may lead to schizophrenia symptoms. We further compare the explanations from our methods to an interpretable classifier and find them to be highly similar. Our proposed methods robustly explain multiple clustering algorithms and could facilitate new insights into many applications. We hope this study will greatly accelerate the development of the field of clustering explainability.

研究动机与目标

• 通过将模型无关的可解释性方法适应到无监督聚类，提升聚类可解释性。
• 在多种聚类算法中提供全局与局部可解释的特征重要性。
• 在低维合成数据和来自 fMRI 的高维脑连接数据上展示其效用。

提出的方法

• 开发全局置换百分比变化（G2PC），用于量化跨聚类算法的特征重要性。
• 开发局部扰动百分比变化（L2PC），用于量化单个样本的特征重要性。
• 展示在多种聚类算法中的适用性（算法无关）。
• 在合成数据集和高维静息态 fMRI 连接数据上验证解释。
• 将解释结果与可解释分类器进行比较以评估相似性。

实验结果

研究问题

• RQ1 模型无关的可解释性技术是否可以适配用于解释无监督聚类？
• RQ2 G2PC 和 L2PC 是否在不同聚类算法下全局与逐样本层面都提供稳定且有意义的特征重要性？
• RQ3 解释是否与可解释分类器的解释以及现有脑连接文献中的解释一致？

主要发现

• G2PC 与 L2PC 能在多种聚类方法中全局和局部地成功识别特征重要性。
• 这些方法易于实现，并在聚类算法中具有广泛的适用性。
• 来自精神分裂症组和对照组的 fMRI 连接性数据的解释与现有文献一致，并为脑连接性变化提供新见解。
• 所提出方法的解释与可解释分类器的解释高度相似。