Correlation Clustering with Adaptive Similarity Queries

Bressan, Marco; Cesa-Bianchi, Nicolo; Paudice, Andrea; Vitale, Fabio

Document type :

Communication dans un congrès avec actes

Title :

Correlation Clustering with Adaptive Similarity Queries

Author(s) :

Bressan, Marco [Auteur]
Università degli Studi di Roma "La Sapienza" = Sapienza University [Rome] [UNIROMA]
Cesa-Bianchi, Nicolo [Auteur]
Dipartimento di Scienze dell'Informazione [Milano]
Paudice, Andrea [Auteur]
Università degli Studi di Milano = University of Milan [UNIMI]
Vitale, Fabio [Auteur]
Machine Learning in Information Networks [MAGNET]

Conference title :

Conference on Neural Information Processing Systems

City :

Vancouver

Country :

Canada

Start date of the conference :

2019-12-08

HAL domain(s) :

Informatique [cs]/Intelligence artificielle [cs.AI]

English abstract : [en]

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. ...
Show more >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.Show less >

Language :

Anglais

Peer reviewed article :

Oui

Audience :

Internationale

Popular science :

Non

Collections :

Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189

Source :

Harvested from HAL

Files

https://hal.inria.fr/hal-02376961/document
Open access
Access the document

http://arxiv.org/pdf/1905.11902
Open access
Access the document

https://hal.inria.fr/hal-02376961/document
Open access
Access the document

https://hal.inria.fr/hal-02376961/document
Open access
Access the document

document
Open access
Access the document

1905.11902.pdf
Open access
Access the document

1905.11902
Open access
Access the document

Correlation Clustering with Adaptive ... BibTeX CSV Excel RIS

Files

Correlation Clustering with Adaptive ...

BibTeX

CSV

Excel

RIS