Efficient Algorithms for Generating Provably Near-Optimal Cluster Descriptors for Explainability
From MaRDI portal
Publication:6334274
arXiv2002.02487MaRDI QIDQ6334274
Andrew Warren, Anil Vullikanti, Aparna Gupta, Ian Davidson, Prathyush Sambaturu, S. S. Ravi
Publication date: 6 February 2020
Abstract: Improving the explainability of the results from machine learning methods has become an important research goal. Here, we study the problem of making clusters more interpretable by extending a recent approach of [Davidson et al., NeurIPS 2018] for constructing succinct representations for clusters. Given a set of objects , a partition of (into clusters), and a universe of tags such that each element in is associated with a subset of tags, the goal is to find a representative set of tags for each cluster such that those sets are pairwise-disjoint and the total size of all the representatives is minimized. Since this problem is NP-hard in general, we develop approximation algorithms with provable performance guarantees for the problem. We also show applications to explain clusters from datasets, including clusters of genomic sequences that represent different threat levels.
Has companion code repository: https://github.com/prathyush6/ExplainabilityCodeAAAI20
Combinatorics in computer science (68R05) Approximation algorithms (68W25) General topics in artificial intelligence (68T01)
This page was built for publication: Efficient Algorithms for Generating Provably Near-Optimal Cluster Descriptors for Explainability
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6334274)
