Comparing Euclidean and Hyperbolic K-Means for Generalized Category Discovery

• URL: http://arxiv.org/abs/2602.04932v1
• Date: Wed, 04 Feb 2026 12:40:33 GMT
• Title: Comparing Euclidean and Hyperbolic K-Means for Generalized Category Discovery
• Abstract summary: We present Hyperbolic Clustered GCD (HC-GCD)<n>HC-GCD learns embeddings in the Lorentz Hyperboloid model of hyperbolic geometry, and clusters these embeddings directly in hyperbolic space using a hyperbolic K-Means algorithm.<n>We show that using hyperbolic K-Means leads to better accuracy than Euclidean K-Means.
• Score: 21.17471771009869
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Hyperbolic representation learning has been widely used to extract implicit hierarchies within data, and recently it has found its way to the open-world classification task of Generalized Category Discovery (GCD). However, prior hyperbolic GCD methods only use hyperbolic geometry for representation learning and transform back to Euclidean geometry when clustering. We hypothesize this is suboptimal. Therefore, we present Hyperbolic Clustered GCD (HC-GCD), which learns embeddings in the Lorentz Hyperboloid model of hyperbolic geometry, and clusters these embeddings directly in hyperbolic space using a hyperbolic K-Means algorithm. We test our model on the Semantic Shift Benchmark datasets, and demonstrate that HC-GCD is on par with the previous state-of-the-art hyperbolic GCD method. Furthermore, we show that using hyperbolic K-Means leads to better accuracy than Euclidean K-Means. We carry out ablation studies showing that clipping the norm of the Euclidean embeddings leads to decreased accuracy in clustering unseen classes, and increased accuracy for seen classes, while the overall accuracy is dataset dependent. We also show that using hyperbolic K-Means leads to more consistent clusters when varying the label granularity.

Related papers

• Hyperbolic Gaussian Blurring Mean Shift: A Statistical Mode-Seeking Framework for Clustering in Curved Spaces [15.555757275390846]
  Clustering is a fundamental unsupervised learning task for uncovering patterns in data.<n>In this work, we introduce HypeGBMS, a novel extension of GBMS to hyperbolic space.<n>Our method replaces Euclidean computations with hyperbolic distances and employs Mbius-weighted means to ensure that all updates remain consistent with the geometry of the space.
  arXiv  Detail & Related papers  (2025-12-12T10:40:26Z)
• Hyperbolic Category Discovery [12.654574453480635]
  Generalized Category Discovery (GCD) aims to categorize all images in the unlabelled subset, regardless of whether they belong to known or unknown classes.<n>Hyperbolic framework for learning hierarchy-aware representations and classifiers for GCD is presented.
  arXiv  Detail & Related papers  (2025-04-08T15:12:33Z)
• Clustering in hyperbolic balls [0.0]
  We introduce the $k$-means clustering in hyperbolic balls, based on the novel definition of barycenter.<n>Second, we present the expectation-maximization (EM) algorithm for learning mixtures of novel probability distributions in hyperbolic balls.
  arXiv  Detail & Related papers  (2025-01-31T16:03:06Z)
• Self-Supervised Graph Embedding Clustering [70.36328717683297]
  K-means one-step dimensionality reduction clustering method has made some progress in addressing the curse of dimensionality in clustering tasks. We propose a unified framework that integrates manifold learning with K-means, resulting in the self-supervised graph embedding framework.
  arXiv  Detail & Related papers  (2024-09-24T08:59:51Z)
• Hyperbolic Delaunay Geometric Alignment [52.835250875177756]
  We propose a similarity score for comparing datasets in a hyperbolic space. The core idea is counting the edges of the hyperbolic Delaunay graph connecting datapoints across the given sets. We provide an empirical investigation on synthetic and real-life biological data and demonstrate that HyperDGA outperforms the hyperbolic version of classical distances between sets.
  arXiv  Detail & Related papers  (2024-04-12T17:14:58Z)
• Hyperbolic vs Euclidean Embeddings in Few-Shot Learning: Two Sides of the Same Coin [49.12496652756007]
  We show that the best few-shot results are attained for hyperbolic embeddings at a common hyperbolic radius. In contrast to prior benchmark results, we demonstrate that better performance can be achieved by a fixed-radius encoder equipped with the Euclidean metric.
  arXiv  Detail & Related papers  (2023-09-18T14:51:46Z)
• Rethinking k-means from manifold learning perspective [122.38667613245151]
  We present a new clustering algorithm which directly detects clusters of data without mean estimation. Specifically, we construct distance matrix between data points by Butterworth filter. To well exploit the complementary information embedded in different views, we leverage the tensor Schatten p-norm regularization.
  arXiv  Detail & Related papers  (2023-05-12T03:01:41Z)
• Geometry Contrastive Learning on Heterogeneous Graphs [50.58523799455101]
  This paper proposes a novel self-supervised learning method, termed as Geometry Contrastive Learning (GCL) GCL views a heterogeneous graph from Euclidean and hyperbolic perspective simultaneously, aiming to make a strong merger of the ability of modeling rich semantics and complex structures. Extensive experiments on four benchmarks data sets show that the proposed approach outperforms the strong baselines.
  arXiv  Detail & Related papers  (2022-06-25T03:54:53Z)
• Hyperbolic Hierarchical Knowledge Graph Embeddings for Link Prediction in Low Dimensions [11.260501547769636]
  We propose a novel KGE model called $textbfHyp$erbolic $textbfH$ierarchical $textbfKGE$ (HypHKGE) This model introduces attention-based learnable curvatures for hyperbolic space, which helps preserve rich semantic hierarchies. Experiments demonstrate the effectiveness of the proposed HypHKGE model on the three benchmark datasets.
  arXiv  Detail & Related papers  (2022-04-28T03:41:41Z)
• Differentiating through the Fr\'echet Mean [51.32291896926807]
  Fr'echet mean is a generalization of the Euclidean mean. We show how to differentiate through the Fr'echet mean for arbitrary Riemannian manifold. This fully integrates the Fr'echet mean into the hyperbolic neural network pipeline.
  arXiv  Detail & Related papers  (2020-02-29T19:49:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.