Pith. sign in

REVIEW 2 cited by

Geometry-aware Distance Measure for Diverse Hierarchical Structures in Hyperbolic Spaces

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2506.18533 v1 pith:QECPKD3Z submitted 2025-06-23 cs.CV

Geometry-aware Distance Measure for Diverse Hierarchical Structures in Hyperbolic Spaces

classification cs.CV
keywords distancehierarchicalhyperboliclearningstructuresdataspacesmeasure
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Learning in hyperbolic spaces has attracted increasing attention due to its superior ability to model hierarchical structures of data. Most existing hyperbolic learning methods use fixed distance measures for all data, assuming a uniform hierarchy across all data points. However, real-world hierarchical structures exhibit significant diversity, making this assumption overly restrictive. In this paper, we propose a geometry-aware distance measure in hyperbolic spaces, which dynamically adapts to varying hierarchical structures. Our approach derives the distance measure by generating tailored projections and curvatures for each pair of data points, effectively mapping them to an appropriate hyperbolic space. We introduce a revised low-rank decomposition scheme and a hard-pair mining mechanism to mitigate the computational cost of pair-wise distance computation without compromising accuracy. We present an upper bound on the low-rank approximation error using Talagrand's concentration inequality, ensuring theoretical robustness. Extensive experiments on standard image classification (MNIST, CIFAR-10 and CIFAR-100), hierarchical classification (5-level CIFAR-100), and few-shot learning tasks (mini-ImageNet, tiered-ImageNet) demonstrate the effectiveness of our method. Our approach consistently outperforms learning methods that use fixed distance measures, with notable improvements on few-shot learning tasks, where it achieves over 5\% gains on mini-ImageNet. The results reveal that adaptive distance measures better capture diverse hierarchical structures, with visualization showing clearer class boundaries and improved prototype separation in hyperbolic spaces.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Learning Taxonomic Trees with Hierarchical Representation Regularization for Large Multimodal Models

    cs.CV 2026-07 conditional novelty 6.0

    HiR² extracts coarse-to-fine visual features from LMM layers and regularizes them with Lorentz entailment cones and unit-sphere dispersive loss, improving hierarchical consistency across models and fine-tuning methods.

  2. Modality Alignment across Trees on Heterogeneous Hyperbolic Manifolds

    cs.CV 2025-10 reject novelty 6.0

    A VLM method aligns hierarchical image and text feature trees across hyperbolic manifolds of different curvatures via an intermediate manifold, but the theoretical justification is flawed.