Hyperbolic Busemann Neural Networks

• URL: http://arxiv.org/abs/2602.18858v2
• Date: Tue, 24 Feb 2026 19:57:12 GMT
• Title: Hyperbolic Busemann Neural Networks
• Authors: Ziheng Chen, Bernhard Schölkopf, Nicu Sebe,
• Abstract summary: 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.<n> BMLR provides compact parameters, a point-to-horosphere distance interpretation, batch-efficient computation, and a Euclidean limit.<n>Experiments on image classification, genome sequence learning, node classification, and link prediction demonstrate improvements in effectiveness and efficiency over prior hyperbolic layers.
• Score: 100.27390895360753
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: 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.

Related papers

• Intrinsic Lorentz Neural Network [49.83037691286893]
  Real-world data frequently exhibit latent hierarchical structures, which can be naturally represented by hyperbolic geometry.<n>We propose the emphIntrinsic Lorentz Neural Network (ILNN), a fully intrinsic hyperbolic architecture that conducts all computations within the Lorentz model.<n>At its core, the network introduces a novel emphpoint-to-hyperplane fully connected layer (FC), replacing traditional Euclidean affine logits with closed-form hyperbolic distances.
  arXiv  Detail & Related papers  (2026-02-27T12:48:05Z)
• EUGens: Efficient, Unified, and General Dense Layers [56.498769704575544]
  We propose a new class of dense layers that generalize standard fully-connected feedforward layers, textbfEfficient, textbfUnimat and textbfGeneral dense layers (EUGens)<n>EUGens leverage random features to approximate standard FFLs and go beyond them by incorporating a direct dependence on the input norms in their computations.
  arXiv  Detail & Related papers  (2026-01-30T05:01:03Z)
• Siegel Neural Networks [13.967997485149192]
  We propose a novel approach for building discriminative neural networks on Siegel spaces.<n>Our results successfully demonstrate state-of-the-art performance across all datasets.
  arXiv  Detail & Related papers  (2025-11-12T07:47:46Z)
• LipKernel: Lipschitz-Bounded Convolutional Neural Networks via Dissipative Layers [0.0468732641979009]
  We propose a layer-wise parameterization for convolutional neural networks (CNNs) that includes built-in robustness guarantees. Our method Lip Kernel directly parameterizes dissipative convolution kernels using a 2-D Roesser-type state space model. We show that the run-time using our method is orders of magnitude faster than state-of-the-art Lipschitz-bounded networks.
  arXiv  Detail & Related papers  (2024-10-29T17:20:14Z)
• Matrix Manifold Neural Networks++ [18.385670036798707]
  We design fully-connected layers for SPD neural networks. We propose a method for performing backpropagation with the Grassmann logarithmic map in the projector perspective.
  arXiv  Detail & Related papers  (2024-05-29T15:47:35Z)
• Enhancing lattice kinetic schemes for fluid dynamics with Lattice-Equivariant Neural Networks [79.16635054977068]
  We present a new class of equivariant neural networks, dubbed Lattice-Equivariant Neural Networks (LENNs) Our approach develops within a recently introduced framework aimed at learning neural network-based surrogate models Lattice Boltzmann collision operators. Our work opens towards practical utilization of machine learning-augmented Lattice Boltzmann CFD in real-world simulations.
  arXiv  Detail & Related papers  (2024-05-22T17:23:15Z)
• Topology-aware Embedding Memory for Continual Learning on Expanding Networks [63.35819388164267]
  We present a framework to tackle the memory explosion problem using memory replay techniques. PDGNNs with Topology-aware Embedding Memory (TEM) significantly outperform state-of-the-art techniques.
  arXiv  Detail & Related papers  (2024-01-24T03:03:17Z)
• Heterogenous Memory Augmented Neural Networks [84.29338268789684]
  We introduce a novel heterogeneous memory augmentation approach for neural networks. By introducing learnable memory tokens with attention mechanism, we can effectively boost performance without huge computational overhead. We show our approach on various image and graph-based tasks under both in-distribution (ID) and out-of-distribution (OOD) conditions.
  arXiv  Detail & Related papers  (2023-10-17T01:05:28Z)
• Data Topology-Dependent Upper Bounds of Neural Network Widths [52.58441144171022]
  We first show that a three-layer neural network can be designed to approximate an indicator function over a compact set. This is then extended to a simplicial complex, deriving width upper bounds based on its topological structure. We prove the universal approximation property of three-layer ReLU networks using our topological approach.
  arXiv  Detail & Related papers  (2023-05-25T14:17:15Z)
• Exploring the Approximation Capabilities of Multiplicative Neural Networks for Smooth Functions [9.936974568429173]
  We consider two classes of target functions: generalized bandlimited functions and Sobolev-Type balls. Our results demonstrate that multiplicative neural networks can approximate these functions with significantly fewer layers and neurons. These findings suggest that multiplicative gates can outperform standard feed-forward layers and have potential for improving neural network design.
  arXiv  Detail & Related papers  (2023-01-11T17:57:33Z)
• Hyperbolic Neural Networks++ [66.16106727715061]
  We generalize the fundamental components of neural networks in a single hyperbolic geometry model, namely, the Poincar'e ball model. Experiments show the superior parameter efficiency of our methods compared to conventional hyperbolic components, and stability and outperformance over their Euclidean counterparts.
  arXiv  Detail & Related papers  (2020-06-15T08:23:20Z)

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.