# On Seeking Consensus Between Document Similarity Measures

## TL;DR

This paper explores consensus clustering methods, demonstrating that using a complement of Rand Index favors the total-separation partition where each element is isolated.

## Contribution

It introduces a novel application of the complement of Rand Index in consensus clustering, highlighting its tendency to select the total-separation partition.

## Key findings

- Using the complement of Rand Index leads to the total-separation partition.
- Consensus clustering with this measure favors maximum separation.
- The approach provides insights into cluster similarity evaluation.

## Abstract

This paper investigates the application of consensus clustering and meta-clustering to the set of all possible partitions of a data set. We show that when using a "complement" of Rand Index as a measure of cluster similarity, the total-separation partition, putting each element in a separate set, is chosen.