# Towards Practical Explainability with Cluster Descriptors

arXiv: https://arxiv.org/abs/2210.10662 · HTML: https://mlsanity.com/paper/2210.10662/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 37 references that are in the map.
- First posted on arXiv 18 Oct 2022.

## Builds on (most cited first, 9 of 9)

- [Metrics for Explainable AI: Challenges and Prospects](https://mlsanity.com/paper/1812.04608/) (2018)
- [Ising formulations of many NP problems](https://mlsanity.com/paper/1302.5843/) (2013)
- [AGATHA: Automatic Graph-mining And Transformer based Hypothesis generation Approach](https://mlsanity.com/paper/2002.05635/) (2020)
- [Layer VQE: A Variational Approach for Combinatorial Optimization on Noisy Quantum Computers](https://mlsanity.com/paper/2102.05566/) (2021)
- [MOLIERE: Automatic Biomedical Hypothesis Generation System](https://mlsanity.com/paper/1702.06176/) (2017)
- [Multilevel Combinatorial Optimization Across Quantum Architectures](https://mlsanity.com/paper/1910.09985/) (2019)
- [Efficient Algorithms for Generating Provably Near-Optimal Cluster Descriptors for Explainability](https://mlsanity.com/paper/2002.02487/) (2020)
- [Evaluating Ising Processing Units with Integer Programming](https://mlsanity.com/paper/1707.00355/) (2017)
- [Scaling laws and dynamics of hashtags on Twitter](https://mlsanity.com/paper/2004.12707/) (2020)

## Built on by (most cited first, 1 of 1)

- [Disjunctive and Conjunctive Normal Form Explanations of Clusters Using Auxiliary Information](https://mlsanity.com/paper/2504.20846/) (2025)

## Abstract (arXiv)

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 π, 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.