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

• URL: http://arxiv.org/abs/2608.25199v1
• Date: Tue, 25 Aug 2026 22:42:20 GMT
• Title: Hyperbolic Latent Geometry for Tree-Structured Prototype Networks: A Local-vs-Global Trade-off
• Abstract summary: We study a tree-structured regularizer over class-prototype layouts in a hierarchical-classification model.<n>We find that Poincare prototypes preserve the topology of the nearest-neighbor graph in latent space substantially better than matched Euclidean prototypes.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Tree-Based Formalization of Multi-Agent Complementarity in Human-AI Interactions [0.3384279376065155]
  Complementarity is the case in which a human--AI interaction outperforms the best prediction benchmark available among its members.<n>Existing frameworks do not model how agents' predictions compose into workflow-sensitive multi-agent protocols.<n>We close this gap by introducing a tree-based formalization of complementarity in multi-agent HAI.
  arXiv  Detail & Related papers  (2026-06-03T12:02:19Z)
• Hinge Regression Trees and HRT-Boost: Newton-Optimized Oblique Learning for Compact Tabular Models [18.386166970880478]
  We present the Hinge Tree (HRT) framework which reframes each oblique split as a nonlinear least-squares problem.<n>We propose HRT-Boost, a mathematically synergistic ensemble extension that node-level Newton updates with stagewise functional gradient descent.
  arXiv  Detail & Related papers  (2026-05-22T09:33:20Z)
• Hyperbolic Enhanced Representation Learning for Incomplete Multi-view Clustering [57.38215918201251]
  We propose HERL, a Hyperbolic Enhanced Representation Learning framework for Incomplete Multi-View Clustering.<n> operating within the Poincaré ball, HERL constructs a structure-aware latent space to enhance representation learning.<n>We show that HERL consistently outperforms state-of-the-art approaches.
  arXiv  Detail & Related papers  (2026-04-18T10:50:46Z)
• ARGENT: Adaptive Hierarchical Image-Text Representations [12.724220731465392]
  We introduce a stronger hyperbolic VLM baseline ARGENT, Adaptive hieRarchical imaGe-tExt represeNTation.<n>This paper introduces a stronger hyperbolic VLM baseline ARGENT, Adaptive hieRarchical imaGe-tExt represeNTation.
  arXiv  Detail & Related papers  (2026-03-24T15:14:12Z)
• Regularized Online RLHF with Generalized Bilinear Preferences [68.44113000390544]
  We consider the problem of contextual online RLHF with general preferences.<n>We adopt the Generalized Bilinear Preference Model to capture preferences via low-rank, skew-symmetric matrices.<n>We prove that the dual gap of the greedy policy is bounded by the square of the estimation error.
  arXiv  Detail & Related papers  (2026-02-26T15:27:53Z)
• Hinge Regression Tree: A Newton Method for Oblique Regression Tree Splitting [18.562483381753804]
  We present the Hinge Regression Tree (HRT), which reframes each split as a non-linear least-squares problem over two linear predictors.<n>We analyze this node-level optimization and, for a backtracking line-search variant, prove that the local objective decreases monotonically and converges.<n>We show on synthetic and real-world benchmarks that HRT matches or outperforms single-tree baselines with more compact structures.
  arXiv  Detail & Related papers  (2026-02-05T06:49:01Z)
• BrepGPT: Autoregressive B-rep Generation with Voronoi Half-Patch [61.20046418942948]
  Boundary representation (B-rep) is the de facto standard for CAD model representation in modern industrial design.<n>We present BrepGPT, a single-stage autoregressive framework for B-rep generation.
  arXiv  Detail & Related papers  (2025-11-27T07:16:53Z)
• Mixed-curvature decision trees and random forests [0.8658819591381167]
  Decision trees (DTs) and their random forest (RF) extensions are workhorses of classification and regression in Euclidean spaces.<n>We extend DT and RF algorithms to product manifold products of several hyperbolic, hyperspherical, or Euclidean components.<n>Our novel angular reformulation respects manifold geometry while preserving the algorithmic properties that make decision trees effective.
  arXiv  Detail & Related papers  (2024-10-03T00:48:07Z)
• Asymmetric Certified Robustness via Feature-Convex Neural Networks [11.605936648692543]
  We show that an ICNN can be generalizationd to an adversarial network. Experiments show that the network is far more efficient than any competitive baseline.
  arXiv  Detail & Related papers  (2023-02-03T19:17:28Z)
• SGA: A Robust Algorithm for Partial Recovery of Tree-Structured Graphical Models with Noisy Samples [75.32013242448151]
  We consider learning Ising tree models when the observations from the nodes are corrupted by independent but non-identically distributed noise. Katiyar et al. (2020) showed that although the exact tree structure cannot be recovered, one can recover a partial tree structure. We propose Symmetrized Geometric Averaging (SGA), a more statistically robust algorithm for partial tree recovery.
  arXiv  Detail & Related papers  (2021-01-22T01:57:35Z)
• Rethinking Learnable Tree Filter for Generic Feature Transform [71.77463476808585]
  Learnable Tree Filter presents a remarkable approach to model structure-preserving relations for semantic segmentation. To relax the geometric constraint, we give the analysis by reformulating it as a Markov Random Field and introduce a learnable unary term. For semantic segmentation, we achieve leading performance (82.1% mIoU) on the Cityscapes benchmark without bells-and-whistles.
  arXiv  Detail & Related papers  (2020-12-07T07:16:47Z)
• Convex Polytope Trees [57.56078843831244]
  convex polytope trees (CPT) are proposed to expand the family of decision trees by an interpretable generalization of their decision boundary. We develop a greedy method to efficiently construct CPT and scalable end-to-end training algorithms for the tree parameters when the tree structure is given.
  arXiv  Detail & Related papers  (2020-10-21T19:38:57Z)

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.