Saved in:
Bibliographic Details
Main Authors: Fan, Chenglin, Shin, Kijun
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.13533
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908408892882944
author Fan, Chenglin
Shin, Kijun
author_facet Fan, Chenglin
Shin, Kijun
contents Clustering is a fundamental task in unsupervised learning. Previous research has focused on learning-augmented $k$-means in Euclidean metrics, limiting its applicability to complex data representations. In this paper, we generalize learning-augmented $k$-clustering to operate on general metrics, enabling its application to graph-structured and non-Euclidean domains. Our framework also relaxes restrictive cluster size constraints, providing greater flexibility for datasets with imbalanced or unknown cluster distributions. Furthermore, we extend the hardness of query complexity to general metrics: under the Exponential Time Hypothesis (ETH), we show that any polynomial-time algorithm must perform approximately $Ω(k / α)$ queries to achieve a $(1 + α)$-approximation. These contributions strengthen both the theoretical foundations and practical applicability of learning-augmented clustering, bridging gaps between traditional methods and real-world challenges.
format Preprint
id arxiv_https___arxiv_org_abs_2506_13533
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Learning Augmented Graph $k$-Clustering
Fan, Chenglin
Shin, Kijun
Machine Learning
Data Structures and Algorithms
Clustering is a fundamental task in unsupervised learning. Previous research has focused on learning-augmented $k$-means in Euclidean metrics, limiting its applicability to complex data representations. In this paper, we generalize learning-augmented $k$-clustering to operate on general metrics, enabling its application to graph-structured and non-Euclidean domains. Our framework also relaxes restrictive cluster size constraints, providing greater flexibility for datasets with imbalanced or unknown cluster distributions. Furthermore, we extend the hardness of query complexity to general metrics: under the Exponential Time Hypothesis (ETH), we show that any polynomial-time algorithm must perform approximately $Ω(k / α)$ queries to achieve a $(1 + α)$-approximation. These contributions strengthen both the theoretical foundations and practical applicability of learning-augmented clustering, bridging gaps between traditional methods and real-world challenges.
title Learning Augmented Graph $k$-Clustering
topic Machine Learning
Data Structures and Algorithms
url https://arxiv.org/abs/2506.13533