From Clustering to Cluster Explanations via Neural Networks
This addresses the need for explainability in clustering, a gap in Explainable AI, which has primarily focused on supervised learning, offering a novel solution for practitioners in data analysis and machine learning.
The paper tackles the problem of explaining cluster assignments in unsupervised learning by proposing a framework that rewrites clustering models as neural networks, enabling efficient and reliable feature attribution, with demonstrations showing its ability to assess cluster quality and extract insights from data.
A recent trend in machine learning has been to enrich learned models with the ability to explain their own predictions. The emerging field of Explainable AI (XAI) has so far mainly focused on supervised learning, in particular, deep neural network classifiers. In many practical problems however, label information is not given and the goal is instead to discover the underlying structure of the data, for example, its clusters. While powerful methods exist for extracting the cluster structure in data, they typically do not answer the question why a certain data point has been assigned to a given cluster. We propose a new framework that can, for the first time, explain cluster assignments in terms of input features in an efficient and reliable manner. It is based on the novel insight that clustering models can be rewritten as neural networks - or 'neuralized'. Cluster predictions of the obtained networks can then be quickly and accurately attributed to the input features. Several showcases demonstrate the ability of our method to assess the quality of learned clusters and to extract novel insights from the analyzed data and representations.