arXiv Machine Learning June 17, 2026 By T. Mitchell Roddenberry, Richard G. Baraniuk

Finsler Geometry, Graph Neural Networks, and You

Read the original on arXiv Machine Learning →

arXiv:2606. 17185v1 Announce Type: new Abstract: Graph neural network architectures based on the graph Laplacian approximate the Laplace-Beltrami operator, thus limiting their application to isotropic operators.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

diffusion

arXiv Machine Learning

4d ago

A Finslerian Approach for Embedding Directed Data

arXiv:2609.37649v1 Announce Type: cross Abstract: Many datasets carry an intrinsic directionality: citations point backward in time, cells differentiate along lineages, and traffic follows preferred...

By Gwendal Debaussart-Joniec (CB, ENS Paris Saclay), Th\'eau Blanchard (HeKA | U1346, GE Healthcare), Argyris Kalogeratos (CB, ENS Paris Saclay)

rag diffusion

arXiv AI

Aug 26

Ollivier-Ricci Curvature of Riemannian Manifolds and Directed Graphs with Applications to Graph Neural Networks

arXiv:2604.14211v2 Announce Type: replace-cross Abstract: This thesis is an exposition of Ollivier-Ricci Curvature of metric spaces as introduced by Yann Ollivier, which is based upon the 1-Wasserste...

By Eleanor P Wiesler

arXiv Machine Learning

Sep 15

Consistency of augmentation graph and network approximability in contrastive learning

arXiv:2502.04312v3 Announce Type: replace Abstract: Contrastive learning leverages data augmentation to develop feature representation without relying on large labeled datasets. However, despite its...

By Chenghui Li, A. Martina Neuman

arXiv Machine Learning

Jun 17

Manifold GCN: Diffusion-based Convolutional Neural Network for Manifold-valued Graphs

arXiv:2401. 14381v3 Announce Type: replace Abstract: We propose two graph neural network layers for graphs with features in a Riemannian manifold.

By Martin Hanik, Gabriele Steidl, Christoph von Tycowicz

diffusion benchmarks safety

arXiv Machine Learning

Jul 27

Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature

arXiv:2607. 22381v1 Announce Type: new Abstract: Curvature notions on graphs, particularly Ollivier-Ricci and Forman, have emerged as powerful tools for addressing fundamental issues in Graph Neural Networks (GNNs) such as oversmoothing and oversquashing, but rely almost exclusively on local edge-level comparisons and therefore fail to certify how information actually propagates over long distances.

By Rachid Caich, Yassine Abbahaddou

efficiency benchmarks

arXiv Machine Learning

Jun 2

Graph Navier Stokes Networks

arXiv:2605. 21247v3 Announce Type: replace Abstract: Graph Neural Networks (GNNs) have emerged as a cornerstone of deep learning, with most existing methods rooted in graph signal processing and diffusion equations to model message passing.

By Zexing Zhao, Guangsi Shi, Yu Gong, Tianyu Wang, Shirui Pan, Hongye Cheng, Yuxiao Li

diffusion benchmarks

One email a morning, machine-written

Related stories

A Finslerian Approach for Embedding Directed Data

Ollivier-Ricci Curvature of Riemannian Manifolds and Directed Graphs with Applications to Graph Neural Networks

Consistency of augmentation graph and network approximability in contrastive learning

Manifold GCN: Diffusion-based Convolutional Neural Network for Manifold-valued Graphs

Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature

Graph Navier Stokes Networks