Towards Practical Explainability with Cluster Descriptors

TL;DR

This paper introduces a novel explainability model for clustering that identifies minimal, disjoint tag descriptors for clusters, formulated as a quadratic optimization problem suitable for hardware acceleration, demonstrated on real datasets.

Contribution

It proposes a new explainability model that improves cluster interpretability by selecting minimal, disjoint tag descriptors, optimized via quadratic unconstrained binary programming on specialized hardware.

Findings

Model effectively identifies minimal cluster descriptors.

Hardware acceleration significantly speeds up optimization.

Demonstrated on Twitter and PubMed datasets.

Abstract

With the rapid development of machine learning, improving its explainability has become a crucial research goal. We study the problem of making the clusters more explainable by investigating the cluster descriptors. Given a set of objects $S$, a clustering of these objects $\pi$, and a set of tags $T$ that have not participated in the clustering algorithm. Each object in $S$ is associated with a subset of $T$. The goal is to find a representative set of tags for each cluster, referred to as the cluster descriptors, with the constraint that these descriptors we find are pairwise disjoint, and the total size of all the descriptors is minimized. In general, this problem is NP-hard. We propose a novel explainability model that reinforces the previous models in such a way that tags that do not contribute to explainability and do not sufficiently distinguish between clusters are not added to the optimal descriptors. The proposed model is formulated as a quadratic unconstrained binary optimization problem which makes it suitable for solving on modern optimization hardware accelerators. We experimentally demonstrate how a proposed explainability model can be solved on specialized hardware for accelerating combinatorial optimization, the Fujitsu Digital Annealer, and use real-life Twitter and PubMed datasets for use cases.