Skip to content
Log in
Sponsored Design Multi-Agent AI Systems Using MCP and A2A: Engineer your own Pyt Design Multi-Agent AI Systems Using MCP and A2A: Engineer your own Pyt
Preprint

Hyperbolic Latent Geometry for Tree-Structured Prototype Networks: A Local-vs-Global Trade-off

Peter Flo L. Großmann
Aug 2026 · 0 citations · 9 references
Computer Science

TL;DR

The results give an empirical separation, on a real hierarchical-classification problem, between two natural latent geometries for a class-structured regularizer.

Abstract

We study a tree-structured regularizer over class-prototype layouts in a hierarchical-classification model and ask whether the choice of latent manifold for the prototypes (Euclidean R^d vs. the Poincare ball B^d_c) affects how well that regularizer can be satisfied without distorting the data likelihood. The two manifolds differ only in their volume growth: hyperbolic space grows exponentially with radius and embeds trees with provably lower distortion than R^d of matched dimension, so the structured regularizer should be cheaper to satisfy on B^d_c. Across 150 seed-replicated regularized maximum-likelihood fits spanning embedding dimension, curvature, and regularizer strength on WikiArt (27 styles, 81,446 paintings, frozen CLIP ViT-B/16 features), we find a single robust effect: Poincare prototypes preserve the topology of the nearest-neighbor graph in latent space substantially better than matched Euclidean prototypes (sibling recall@5 +8.7 pp, cousin recall +15.2 pp; paired-t p<10^-4, sign agreement 0.94), and the gap holds across three reference-tree definitions (hand-built lineage, CLIP-derived, and DINOv2-derived). On classification, Euclidean prototypes are tied with logistic regression on raw encoder features, indicating no detectable contribution from the latent geometry; only the hyperbolic fit improves on a k-NN encoder baseline for local retrieval. Global tree-fidelity comparisons are unstable across reference trees and we do not claim a winner. The results give an empirical separation, on a real hierarchical-classification problem, between two natural latent geometries for a class-structured regularizer.

arXiv Semantic Scholar
View source

Similar papers

Jul 2026

Distance-Preserving Embeddings in Inhomogeneous Random Graphs

This approach demonstrates that models trained on small-scale random graphs learn to extract universal distance-preserving features, achieving robust generalization to large-scale, real-world networks that match or exceed the fidelity of classical, exact landmark-based embeddings.

My Le, Luana Ruiz, Souvik Dhara · 0 citations
Preprint Aug 2026

Spectral Embeddings of Degree-$\alpha$ Laplacians in Random Dot Product Graphs

A continuum of degree-normalized spectral embeddings that includes these commonly used choices as special cases is studied, and a row-wise central limit theorem is established under a random dot product graph model for this family of embeddings.

John Park, Ning Hao · 0 citations
Open access Aug 2026

Feature-Graph-Guided Adaptive Sparse NMF with Anchor Dual Graphs Under the Logarithmic Framework for Data Clustering

This paper proposes a feature-graph-guided adaptive Log-L2,1 sparse NMF with anchor dual graphs under a logarithmic framework that jointly integrate sample structure preservation, feature structure preservation, and feature-aware sparse learning within a unified graph-NMF model.

Quanrun Li, Tao Ma, Fangchen Xu et al. · 0 citations
Preprint Aug 2026

A Fixed-Radius Distance-Band Benchmark for Dimensionality-Reduction Fidelity

A membership-restricted Shepard rho resolves single-point and minority-population questions that many-pair statistics cannot -- questions on which even DREAMS, a recent local-plus-global hybrid, fails silently.

Y. Takaeda · 0 citations
Conference Jul 2026

LightConeFM: Unconstrained Lorentz Embeddings for Collaborative Filtering

Hyperbolic embedding methods for collaborative filtering constrain all representations to the hyperboloid manifold, imposing a single geometry regardless of data characteristics. We introduce LightConeFM, which removes this constraint and allows embeddings to freely occupy any causal region of Lorentz-Minkowski space-timelike, lightlike, or spacelike-using only standard gradient descent without Riemannian optimization. Experiments on four real-world datasets reveal two consistent findings: (1) unconstrained embeddings outperform their constrained counterparts on every dataset (up to +7.0% AUC), and (2) the learned causal zone distribution predicts where hyperbolic geometry provides benefit over Euclidean alternatives (Pearson $r=0.94$, Spearman $\rho=1.0)$ -datasets with predominantly timelike users exhibit the largest gains, while predominantly spacelike datasets are better served by Euclidean methods. On a job recommendation dataset, LightConeFM achieves +5.99% AUC improvement in cold-start settings, indicating particular value for sparse, hierarchical domains.

K. Uyar · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.