mlsanityData to 14 Oct 2026

Projections of Model Spaces for Latent Graph Inference

arXiv 2303.11754 ↗First posted 21 Mar 2023cs.LGcited by 9

Not on the map. Why?

Abstract (arXiv)

Graph Neural Networks leverage the connectivity structure of graphs as an inductive bias. Latent graph inference focuses on learning an adequate graph structure to diffuse information on and improve the downstream performance of the model. In this work we employ stereographic projections of the hyperbolic and spherical model spaces, as well as products of Riemannian manifolds, for the purpose of latent graph inference. Stereographically projected model spaces achieve comparable performance to their non-projected counterparts, while providing theoretical guarantees that avoid divergence of the spaces when the curvature tends to zero. We perform experiments on both homophilic and heterophilic graphs.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 15 of its 22 references that are in the map. First posted on arXiv 21 Mar 2023.

Builds on

15 of 22 references.

References · 15

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2017Graph Attention Networkscited by 8,923
  3. 2021Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gaugescited by 1,167
  4. 2021Understanding over-squashing and bottlenecks on graphs via curvaturecited by 478
  5. 2019Diffusion Improves Graph Learningcited by 414
  6. 2020Graph Structure Learning for Robust Graph Neural Networkscited by 371
  7. 2019Learning Discrete Structures for Graph Neural Networkscited by 231
  8. 2020Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddingscited by 214
  9. 2019Mixed-curvature Variational Autoencoderscited by 86
  10. 2020Differentiable Graph Module (DGM) for Graph Convolutional Networkscited by 86
  11. 2021Beltrami Flow and Neural Diffusion on Graphscited by 84
  12. 2022Sheaf Neural Networks with Connection Laplacianscited by 65
3 more
  1. 2021Learning Signal-Agnostic Manifolds of Neural Fieldscited by 45
  2. 2020Latent-Graph Learning for Disease Predictioncited by 39
  3. 2022Latent Graph Inference using Product Manifoldscited by 23

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 4; 2024: 2; 2025: 2; 2026: 1.

9 papers.

  1. 2025On Vanishing Gradients, Over-Smoothing, and Over-Squashing in GNNs: Bridging Recurrent and Graph Learningcited by 43
  2. 2023Neural Latent Geometry Search: Product Manifold Inference via Gromov-Hausdorff-Informed Bayesian Optimizationcited by 18
  3. 2024Rough Transformers: Lightweight and Continuous Time Series Modelling through Signature Patchingcited by 16
  4. 2023Neural Snowflakes: Universal Latent Graph Inference via Trainable Latent Geometriescited by 6
  5. 2023AMES: A Differentiable Embedding Space Selection Framework for Latent Graph Inferencecited by 3
  6. 2023Gromov-Hausdorff Distances for Comparing Product Manifolds of Model Spacescited by 0
  7. 2024Metric Learning for Clifford Group Equivariant Neural Networkscited by 0
  8. 2025Bridging Graph and State-Space Modeling for Intensive Care Unit Length of Stay Predictioncited by 0
  9. 2026k-Maximum Inner Product Attention for Graph Transformers and the Expressive Power of GraphGPScited by 0