Correlation Clustering with Adaptive Similarity Queries - Archive ouverte HAL Access content directly
Conference Papers Year :

## Correlation Clustering with Adaptive Similarity Queries

(1) , (2) , (3) , (4)
1
2
3
4
Marco Bressan
• Function : Author
• PersonId : 945551
Andrea Paudice
• Function : Author
Fabio Vitale
• Function : Author

#### Abstract

In correlation clustering, we are given $n$ objects together with a binary similarity score between each pair of them. The goal is to partition the objects into clusters so to minimise the disagreements with the scores. In this work we investigate correlation clustering as an active learning problem: each similarity score can be learned by making a query, and the goal is to minimise both the disagreements and the total number of queries. On the one hand, we describe simple active learning algorithms, which provably achieve an almost optimal trade-off while giving cluster recovery guarantees, and we test them on different datasets. On the other hand, we prove information-theoretical bounds on the number of queries necessary to guarantee a prescribed disagreement bound. These results give a rich characterization of the trade-off between queries and clustering error.

### Dates and versions

hal-02376961 , version 1 (22-11-2019)

### Identifiers

• HAL Id : hal-02376961 , version 1
• ARXIV :

### Cite

Marco Bressan, Nicolo Cesa-Bianchi, Andrea Paudice, Fabio Vitale. Correlation Clustering with Adaptive Similarity Queries. Conference on Neural Information Processing Systems, Dec 2019, Vancouver, Canada. ⟨hal-02376961⟩

### Export

BibTeX TEI Dublin Core DC Terms EndNote Datacite

51 View