Timezone: »

 
Poster
Correlation Clustering with Adaptive Similarity Queries
Marco Bressan · Nicolò Cesa-Bianchi · Andrea Paudice · Fabio Vitale

Tue Dec 10 10:45 AM -- 12:45 PM (PST) @ East Exhibition Hall B + C #29
in Algorithms -- Clustering »
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.
Keywords: Clustering · Learning Theory · Algorithms · Theory
[ Paper]  [ Poster] 

Author Information

Marco Bressan (Sapienza University of Rome)
Nicolò Cesa-Bianchi (Università degli Studi di Milano)
Andrea Paudice (University of Milan)
Fabio Vitale (University of Lille - INRIA Lille (France))

More from the Same Authors