Saved in:
Bibliographic Details
Main Authors: Chen, Ziheng, Schölkopf, Bernhard, Sebe, Nicu
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.18858
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911466970415104
author Chen, Ziheng
Schölkopf, Bernhard
Sebe, Nicu
author_facet Chen, Ziheng
Schölkopf, Bernhard
Sebe, Nicu
contents Hyperbolic spaces provide a natural geometry for representing hierarchical and tree-structured data due to their exponential volume growth. To leverage these benefits, neural networks require intrinsic and efficient components that operate directly in hyperbolic space. In this work, we lift two core components of neural networks, Multinomial Logistic Regression (MLR) and Fully Connected (FC) layers, into hyperbolic space via Busemann functions, resulting in Busemann MLR (BMLR) and Busemann FC (BFC) layers with a unified mathematical interpretation. BMLR provides compact parameters, a point-to-horosphere distance interpretation, batch-efficient computation, and a Euclidean limit, while BFC generalizes FC and activation layers with comparable complexity. Experiments on image classification, genome sequence learning, node classification, and link prediction demonstrate improvements in effectiveness and efficiency over prior hyperbolic layers. The code is available at https://github.com/GitZH-Chen/HBNN.
format Preprint
id arxiv_https___arxiv_org_abs_2602_18858
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Hyperbolic Busemann Neural Networks
Chen, Ziheng
Schölkopf, Bernhard
Sebe, Nicu
Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
Hyperbolic spaces provide a natural geometry for representing hierarchical and tree-structured data due to their exponential volume growth. To leverage these benefits, neural networks require intrinsic and efficient components that operate directly in hyperbolic space. In this work, we lift two core components of neural networks, Multinomial Logistic Regression (MLR) and Fully Connected (FC) layers, into hyperbolic space via Busemann functions, resulting in Busemann MLR (BMLR) and Busemann FC (BFC) layers with a unified mathematical interpretation. BMLR provides compact parameters, a point-to-horosphere distance interpretation, batch-efficient computation, and a Euclidean limit, while BFC generalizes FC and activation layers with comparable complexity. Experiments on image classification, genome sequence learning, node classification, and link prediction demonstrate improvements in effectiveness and efficiency over prior hyperbolic layers. The code is available at https://github.com/GitZH-Chen/HBNN.
title Hyperbolic Busemann Neural Networks
topic Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2602.18858