Connecting Neural Models Latent Geometries With Relative Geodesic Representations

Abstract

Neural models learn representations of high-dimensional data on low-dimensional manifolds. Multiple factors, including stochasticities in the training process, model architectures, and additional inductive biases, may induce different representations, even when learning the same task on the same data. However, it has recently been shown that when a latent structure is shared between distinct latent spaces, relative distances between representations can be preserved, up to distortions. Building on this idea, we demonstrate that exploiting the differential-geometric structure of latent spaces of neural models, it is possible to capture precisely the transformations between representational spaces trained on similar data distributions. Specifically, we assume that distinct neural models parametrize approximately the same underlying manifold, and introduce a representation based on the pullback metric that captures the intrinsic structure of the latent space, while scaling efficiently to l

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyyu2025connecting

Related papers

• Representing Deep Neural Networks Latent Space Geometries With Graphs (2020)7.50
• Latent Functional Maps: A Spectral Framework For Representation Alignment (2024)3.58
• Gauge Freedom And Metric Dependence In Neural Representation Spaces (2026)0.00
• For Manifold Learning, Deep Neural Networks Can Be Locality Sensitive Hash Functions (2021)0.00
• Randomly Weighted Neuromodulation In Neural Networks Facilitates Learning Of Manifolds Common Across Tasks (2023)0.00
• Neural Bregman Divergences For Distance Learning (2022)0.00
• Renderers Are Good Zero-shot Representation Learners: Exploring Diffusion Latents For Metric Learning (2023)0.60
• Differential Geometric Retrieval Of Deep Features (2017)2.26