Unsupervised Latent Space Alignment with Hyperspherical Geodesic Matching

• URL: http://arxiv.org/abs/2608.28840v1
• Date: Fri, 28 Aug 2026 20:22:44 GMT
• Title: Unsupervised Latent Space Alignment with Hyperspherical Geodesic Matching
• Abstract summary: HGA is a method to optimize a transformation between two latent spaces by maximizing a geometric measure of "fit" between them.<n>It can operate in both an unsupervised and weakly supervised regime.<n>On tasks such as model stitching or multilingual word embedding correspondence recovery, HGA manages to match supervised results with minimal or no supervision.
• Score: 14.1760167030233
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Independently trained neural networks tend to encode the same data with similar latent geometries. These latent geometries are not directly compatible, yet they can be nearly the same up to some class of transformations. While there exists many methods for alignment between different latent spaces, it is typically done using a set of shared sample correspondences, known as anchors. This leaves a fundamental question: are the geometric signatures of different latent spaces representing similar data sufficient to recover an alignment between them? To that end, we introduce HGA (Hyperspherical Gaussian Alignment), a method that directly optimizes a transformation between two latent spaces by maximizing a geometric measure of "fit" between them. Since it is driven by the geometry of the latent spaces rather than paired data, HGA can operate in both an unsupervised and weakly supervised regime. On tasks such as model stitching or multilingual word embedding correspondence recovery, HGA manages to match supervised results with minimal or no supervision.

Related papers

• Rank-Aware Hyperbolic Alignment for Vision-Language Dataset Distillation [54.74045834035952]
  Vision-language dataset distillation (VLDD) compresses a large image-text paired dataset into a small set of synthetic pairs.<n>We propose a rank-aware hyperbolic alignment (RAHA) that combines hierarchical geometry with explicit alignment-capacity control.<n>RAHA demonstrates competitive cross-modal retrieval and improved transfer indicators under fixed budgets.
  arXiv  Detail & Related papers  (2026-06-28T15:41:31Z)
• Multi-Way Representation Alignment [19.53606443098969]
  Current strategies for mapping representations are inherently pairwise, scaling quadratically with the number of models and failing to yield a consistent global reference.<n>We first adapt Generalized Procrustes Analysis (GPA) to construct a shared universe that preserves the internal geometry essential for tasks like model stitching.<n>We then show that strict isometric alignment is suboptimal for retrieval, where agreement-maximizing methods like Canonical Correlation Analysis (CCA) typically prevail.<n>To bridge this gap, we finally propose Geometry-Corrected Procrustes Alignment (GCPA), which establishes a robust GPA-based universe followed by a post-
  arXiv  Detail & Related papers  (2026-02-05T21:33:45Z)
• Dense Semantic Matching with VGGT Prior [49.42199006453071]
  We propose an approach that retains VGGT's intrinsic strengths by reusing early feature stages, fine-tuning later ones, and adding a semantic head for bidirectional correspondences.<n>Our approach achieves superior geometry awareness, matching reliability, and manifold preservation, outperforming previous baselines.
  arXiv  Detail & Related papers  (2025-09-25T14:56:11Z)
• Enforcing Latent Euclidean Geometry in Single-Cell VAEs for Manifold Interpolation [79.27003481818413]
  We introduce FlatVI, a training framework that regularises the latent manifold of discrete-likelihood variational autoencoders towards Euclidean geometry.<n>By encouraging straight lines in the latent space to approximate geodesics on the decoded single-cell manifold, FlatVI enhances compatibility with downstream approaches.
  arXiv  Detail & Related papers  (2025-07-15T23:08:14Z)
• GMapLatent: Geometric Mapping in Latent Space [51.317738404571514]
  Cross-domain generative models based on encoder-decoder AI architectures have attracted much attention in generating realistic images.<n>We introduce a canonical latent space representation based on geometric mapping to align the cross-domain latent spaces in a rigorous and precise manner.<n>Experiments on gray-scale and color images validate the efficiency, efficacy and applicability of GMapLatent.
  arXiv  Detail & Related papers  (2025-03-30T12:02:36Z)
• Neural Spacetimes for DAG Representation Learning [23.54420278189682]
  We propose a class of trainable deep learning-based geometries called Neural Spacetimes.<n>We encode both graph edge weights in its spatial dimensions and causality in the form of edge directionality in its temporal dimensions.<n>Our main theoretical guarantee is a universal embedding theorem, showing that any $k$-point DAG can be embedded into an NST with $1+mathcalO(log(k))$ distortion.
  arXiv  Detail & Related papers  (2024-08-25T16:26:55Z)
• Disentangled Representation Learning with the Gromov-Monge Gap [65.73194652234848]
  Learning disentangled representations from unlabelled data is a fundamental challenge in machine learning.<n>We introduce a novel approach to disentangled representation learning based on quadratic optimal transport.<n>We demonstrate the effectiveness of our approach for quantifying disentanglement across four standard benchmarks.
  arXiv  Detail & Related papers  (2024-07-10T16:51:32Z)
• Grounding Continuous Representations in Geometry: Equivariant Neural Fields [26.567143650213225]
  We propose a novel CNF architecture which uses a geometry-informed cross-attention to condition the NeF on a geometric variable.<n>We show that this approach induces a steerability property by which both field and latent are grounded in geometry.<n>We validate these main properties in a range of tasks including classification, segmentation, forecasting, reconstruction and generative modelling.
  arXiv  Detail & Related papers  (2024-06-09T12:16:30Z)
• GoMVS: Geometrically Consistent Cost Aggregation for Multi-View Stereo [45.5438546016874]
  We propose GoMVS to aggregate geometrically consistent costs, yielding better utilization of adjacent geometries. Our method achieves new state-of-the-art performance on DTU, Tanks & Temple, and ETH3D datasets.
  arXiv  Detail & Related papers  (2024-04-11T17:59:59Z)
• Relative representations enable zero-shot latent space communication [19.144630518400604]
  Neural networks embed the geometric structure of a data manifold lying in a high-dimensional space into latent representations. We show how neural architectures can leverage these relative representations to guarantee, in practice, latent isometry invariance.
  arXiv  Detail & Related papers  (2022-09-30T12:37:03Z)
• RANSAC-Flow: generic two-stage image alignment [53.11926395028508]
  We show that a simple unsupervised approach performs surprisingly well across a range of tasks. Despite its simplicity, our method shows competitive results on a range of tasks and datasets.
  arXiv  Detail & Related papers  (2020-04-03T12:37:58Z)

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.