XClusters: Explainability-first Clustering

TL;DR

This paper introduces XClusters, a novel clustering approach that integrates explainability directly into the clustering process using a joint optimization with decision trees, improving interpretability without sacrificing performance.

Contribution

XClusters presents a holistic clustering method that simultaneously optimizes for cluster quality and decision tree explainability, unlike traditional post-hoc explanation methods.

Findings

Improves explainability of clustering results.

Balances cluster distortion with decision tree simplicity.

Efficient branch-and-bound algorithm for parameter optimization.

Abstract

We study the problem of explainability-first clustering where explainability becomes a first-class citizen for clustering. Previous clustering approaches use decision trees for explanation, but only after the clustering is completed. In contrast, our approach is to perform clustering and decision tree training holistically where the decision tree's performance and size also influence the clustering results. We assume the attributes for clustering and explaining are distinct, although this is not necessary. We observe that our problem is a monotonic optimization where the objective function is a difference of monotonic functions. We then propose an efficient branch-and-bound algorithm for finding the best parameters that lead to a balance of cluster distortion and decision tree explainability. Our experiments show that our method can improve the explainability of any clustering that fits in our framework.