用反事实解释聚类结果，让非专业人士也能看懂算法决策。
Counterfactual Explanations for Clustering Models
- 通过软评分捕捉聚类的空间信息，引导反事实生成。
- 在5个数据集、2种聚类算法上验证，效果显著提升。
- 适合希望理解聚类结果的非技术用户或模型审计者。
聚类算法依赖复杂的优化过程，对非技术用户而言难以理解。尽管可解释人工智能技术在监督学习中已较成熟，但无监督学习尤其是聚类仍被忽视。此外，‘真实’聚类的定义本身也具有挑战性。为应对这些难题，我们提出一种新型、模型无关的聚类解释方法，基于反事实陈述。该方法采用新颖的软评分机制，捕捉聚类模型利用的空间信息，并借鉴监督学习中的先进贝叶斯反事实生成器，以生成高质量解释。我们在五个数据集和两种聚类算法上进行了评估，结果表明引入软评分显著提升了反事实搜索的效果。
原文摘要 · Abstract (English)
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.
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。