arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.12632cs.LGcs.AIcs.NE
收藏

聚类模型的反事实解释

Counterfactual Explanations for Clustering Models

Università della Svizzera italiana (USI)(瑞士意大利语大学);ETH Zurich(苏黎世联邦理工学院)

Aurora Spagnol, Kacper Sokol, Pietro Barbiero, Marc Langheinrich, Martin Gjoreski

AI总结:

针对聚类模型难以解释的问题,提出一种模型无关的反事实解释方法,利用软评分引导反事实搜索,在五个数据集和两种聚类算法上显著提升解释质量。

摘要:

聚类算法依赖于复杂的优化过程,这些过程可能难以理解,尤其是对于缺乏技术专长的个人而言。尽管存在许多用于监督机器学习的可解释人工智能技术,但无监督学习——尤其是聚类——在很大程度上被忽视了。使问题更加复杂的是,“真实”聚类的概念本质上难以定义。无监督学习及其可解释性的这些方面使得难以培养对此类方法的信任,并阻碍了它们的采用。为了解决这些挑战,我们提出了一种新的、模型无关的技术,用于通过反事实陈述来解释聚类算法。我们的方法依赖于一种新颖的软评分方法,该方法捕获聚类模型利用的空间信息。它建立在用于监督学习的最先进的贝叶斯反事实生成器之上,以提供高质量的解释。我们在五个数据集和两种聚类算法上评估了其性能,并证明引入软评分来指导反事实搜索显著改善了结果。

英文摘要:

Clustering algorithms rely on complex optimisation processes that may be difficult to comprehend, especially for individuals who lack technical expertise. While many explainable artificial intelligence techniques exist for supervised machine learning, unsupervised learning -- and clustering in particular -- has been largely neglected. To complicate matters further, the notion of a ``true'' cluster is inherently challenging to define. These facets of unsupervised learning and its explainability make it difficult to foster trust in such methods and curtail their adoption. To address these challenges, we propose a new, model-agnostic technique for explaining clustering algorithms with counterfactual statements. Our approach relies on a novel soft-scoring method that captures the spatial information utilised by clustering models. It builds upon a state-of-the-art Bayesian counterfactual generator for supervised learning to deliver high-quality explanations. We evaluate its performance on five datasets and two clustering algorithms, and demonstrate that introducing soft scores to guide counterfactual search significantly improves the results.

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。

↑