Comparing Clusterings: An Axiomatic View
Abstract
This paper views clusterings as elements of a lattice. Distances between clusterings are analyzed in their relationship to the lattice. From this vantage point, we first give an axiomatic characterization of some criteria for comparing clusterings, including the variation of information and the unadjusted Rand index. Then we study other distances between partitions w.r.t these axioms and prove an impossibility result: there is no "sensible" criterion for comparing clusterings that is simultaneously (1) aligned with the lattice of partitions, (2) convexely additive, and (3) bounded.
Cite
Text
Meila. "Comparing Clusterings: An Axiomatic View." International Conference on Machine Learning, 2005. doi:10.1145/1102351.1102424Markdown
[Meila. "Comparing Clusterings: An Axiomatic View." International Conference on Machine Learning, 2005.](https://mlanthology.org/icml/2005/meila2005icml-comparing/) doi:10.1145/1102351.1102424BibTeX
@inproceedings{meila2005icml-comparing,
title = {{Comparing Clusterings: An Axiomatic View}},
author = {Meila, Marina},
booktitle = {International Conference on Machine Learning},
year = {2005},
pages = {577-584},
doi = {10.1145/1102351.1102424},
url = {https://mlanthology.org/icml/2005/meila2005icml-comparing/}
}