A Pragmatic Method for Comparing Clusterings with Overlaps and Outliers
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908902535200768 |
|---|---|
| author | DeWolfe, Ryan Prałat, Paweł Théberge, François |
| author_facet | DeWolfe, Ryan Prałat, Paweł Théberge, François |
| contents | Clustering algorithms are an essential part of the unsupervised data science ecosystem, and extrinsic evaluation of clustering algorithms requires a method for comparing the detected clustering to a ground truth clustering. In a general setting, the detected and ground truth clusterings may have outliers (objects belonging to no cluster), overlapping clusters (objects may belong to more than one cluster), or both, but methods for comparing these clusterings are currently undeveloped. In this note, we define a pragmatic similarity measure for comparing clusterings with overlaps and outliers, show that it has several desirable properties, and experimentally confirm that it is not subject to several common biases afflicting other clustering comparison measures. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_14855 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | A Pragmatic Method for Comparing Clusterings with Overlaps and Outliers DeWolfe, Ryan Prałat, Paweł Théberge, François Machine Learning Social and Information Networks Combinatorics Clustering algorithms are an essential part of the unsupervised data science ecosystem, and extrinsic evaluation of clustering algorithms requires a method for comparing the detected clustering to a ground truth clustering. In a general setting, the detected and ground truth clusterings may have outliers (objects belonging to no cluster), overlapping clusters (objects may belong to more than one cluster), or both, but methods for comparing these clusterings are currently undeveloped. In this note, we define a pragmatic similarity measure for comparing clusterings with overlaps and outliers, show that it has several desirable properties, and experimentally confirm that it is not subject to several common biases afflicting other clustering comparison measures. |
| title | A Pragmatic Method for Comparing Clusterings with Overlaps and Outliers |
| topic | Machine Learning Social and Information Networks Combinatorics |
| url | https://arxiv.org/abs/2602.14855 |