Cold-Start Active Correlation Clustering

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Aronsson, Linus, Wu, Han, Chehreghani, Morteza Haghir
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910044490039296
author Aronsson, Linus
Wu, Han
Chehreghani, Morteza Haghir
author_facet Aronsson, Linus
Wu, Han
Chehreghani, Morteza Haghir
contents We study active correlation clustering where pairwise similarities are not provided upfront and must be queried in a cost-efficient manner through active learning. Specifically, we focus on the cold-start scenario, where no true initial pairwise similarities are available for active learning. To address this challenge, we propose a coverage-aware method that encourages diversity early in the process. We demonstrate the effectiveness of our approach through several synthetic and real-world experiments.
format Preprint
id arxiv_https___arxiv_org_abs_2509_25376
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Cold-Start Active Correlation Clustering
Aronsson, Linus
Wu, Han
Chehreghani, Morteza Haghir
Machine Learning
Artificial Intelligence
Social and Information Networks
We study active correlation clustering where pairwise similarities are not provided upfront and must be queried in a cost-efficient manner through active learning. Specifically, we focus on the cold-start scenario, where no true initial pairwise similarities are available for active learning. To address this challenge, we propose a coverage-aware method that encourages diversity early in the process. We demonstrate the effectiveness of our approach through several synthetic and real-world experiments.
title Cold-Start Active Correlation Clustering
topic Machine Learning
Artificial Intelligence
Social and Information Networks
url https://arxiv.org/abs/2509.25376