mlsanityData to 14 Oct 2026

Are Cluster Validity Measures (In)valid?

arXiv 2208.01261 ↗First posted 2 Aug 2022stat.ML cs.LGcited by 16

Not on the map. Why?

Abstract (arXiv)

Internal cluster validity measures (such as the Calinski-Harabasz, Dunn, or Davies-Bouldin indices) are frequently used for selecting the appropriate number of partitions a dataset should be split into. In this paper we consider what happens if we treat such indices as objective functions in unsupervised learning activities. Is the optimal grouping with regards to, say, the Silhouette index really meaningful? It turns out that many cluster (in)validity indices promote clusterings that match expert knowledge quite poorly. We also introduce a new, well-performing variant of the Dunn index that is built upon OWA operators and the near-neighbour graph so that subspaces of higher density, regardless of their shapes, can be separated from each other better.

Key facts. Cited by 16 papers in the map (data through 14 Oct 2026). Builds on 2 of its 61 references that are in the map. First posted on arXiv 2 Aug 2022.

Builds on

2 of 61 references.

References · 2

  1. 2013A Literature Survey of Benchmark Functions For Global Optimization Problemscited by 77
  2. 2017The Impact of Random Models on Clustering Similaritycited by 34

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 2; 2023: 2; 2024: 2; 2025: 7; 2026: 3.

16 papers.

Sort:

By area:

  1. 2022A framework for benchmarking clustering algorithmscited by 15
  2. 2023Clustering with minimum spanning trees: How good can it be?cited by 4
  3. 2025HAD-Gen: Human-like and Diverse Driving Behavior Modeling for Controllable Scenario Generationcited by 3
  4. 2022Normalised clustering accuracy: An asymmetric external cluster validity measurecited by 2
  5. 2024On the Use of Relative Validity Indices for Comparing Clustering Approachescited by 2
  6. 2024TopER: Topological Embeddings in Graph Representation Learningcited by 1
  7. 2025Hierarchical clustering with maximum density paths and mixture modelscited by 1
  8. 2025Benchmarking of Clustering Validity Measures Revisitedcited by 1
  9. 2026Cluster Analysis with Resampling for Validation and Exploration (CARVE)cited by 1
  10. 2023A new approach for evaluating internal cluster validation indicescited by 0
  11. 2025An upper bound on the silhouette evaluation metric for clusteringcited by 0
  12. 2025Absolute indices for determining compactness, separability and number of clusterscited by 0
4 more
  1. 2025Visual Model Selection using Feature Importance Clusters in Fairness-Performance Similarity Optimized Spacecited by 0
  2. 2025Multi-view diffusion geometry using intertwined diffusion trajectoriescited by 0
  3. 2026CROCS: A Two-Stage Clustering Framework for Behaviour-Centric Consumer Segmentation with Smart Meter Datacited by 0
  4. 2026Explaining AutoClustering: Uncovering Meta-Feature Contribution in AutoML for Clusteringcited by 0