paper-with-me

홈 › Papers

Identifying the latent space geometry of network models through analysis of curvature

2020-12-19 · Shane Lubold, Arun G. Chandrasekhar, Tyler H. McCormick

A common approach to modeling networks assigns each node to a position on a low-dimensional manifold where distance is inversely proportional to connection likelihood. More positive manifold curvature encourages more and tighter communities; negative curvature induces repulsion. We consistently estimate manifold type, dimension, and curvature from simply connected, complete Riemannian manifolds of constant curvature. We represent the graph as a noisy distance matrix based on the ties between cliques, then develop hypothesis tests to determine whether the observed distances could plausibly be embedded isometrically in each of the candidate geometries. We apply our approach to data-sets from economics and neuroscience.

📄 PDF Abstract BibTeX arXiv:2012.10559

Code (1)

slubold/LS_Geometry

Tasks

PositionSociology

Similar Papers 제목 키워드 기반

Neural Latent Geometry Search: Product Manifold Inference via Gromov-Hausdorff-Informed Bayesian Optimization

2023-09-09 · NeurIPS 2023 11

Recent research indicates that the performance of machine learning models can be improved by aligning the geometry of the latent space with the underlying data structure. Rather than relying solely on Euclidean space, re…

Bayesian OptimizationInductive Bias

Visualizing LLM Latent Space Geometry Through Dimensionality Reduction

2025-11-26 · Alex Ning, Vainateya Rangaraju, Yen-Ling Kuo arxiv

Large language models (LLMs) achieve state-of-the-art results across many natural language tasks, but their internal mechanisms remain difficult to interpret. In this work, we extract, process, and visualize latent state…

Dimensionality Reduction

Decoder ensembling for learned latent geometries

2024-08-14 · Stas Syrota, Pablo Moreno-Muñoz, Søren Hauberg

Latent space geometry provides a rigorous and empirically valuable framework for interacting with the latent variables of deep generative models. This approach reinterprets Euclidean latent spaces as Riemannian through a…

Decoder

Geometry of Deep Generative Models for Disentangled Representations

2019-02-19 · Ankita Shukla, Shagun Uppal, Sarthak Bhagat, Saket Anand 외

Deep generative models like variational autoencoders approximate the intrinsic geometry of high dimensional data manifolds by learning low-dimensional latent-space variables and an embedding function. The geometric prope…

Representation Learning

Unveiling the Latent Space Geometry of Push-Forward Generative Models

2022-07-21 · Thibaut Issenhuth, Ugo Tanielian, Jérémie Mary, David Picard

Many deep generative models are defined as a push-forward of a Gaussian measure by a continuous generator, such as Generative Adversarial Networks (GANs) or Variational Auto-Encoders (VAEs). This work explores the latent…

Face Model