arXiv Machine Learning June 2, 2026 By Yuhan Peng, Junwen Dong, Yuzhi Zeng, Hao Li, Ce Ju, Huitao Feng, Diaaeldin Taha, Anna Wienhard, Kelin Xia

Sheaf Neural Networks on SPD Manifolds: Second-Order Geometric Representation Learning

Read the original on arXiv Machine Learning →

arXiv:2604. 20308v2 Announce Type: replace Abstract: Graph neural networks face two fundamental challenges rooted in the linear structure of Euclidean vector spaces: (1) Current architectures represent geometry through vectors (directions, gradients), yet many tasks require matrix-valued representations that capture relationships between directions-such as how atomic orientations covary in a molecule.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

benchmarks

arXiv Machine Learning

Aug 11

SPD Learn: A Geometric Deep Learning Python Library for Neural Decoding Through Trivialization

arXiv:2602. 22895v2 Announce Type: replace-cross Abstract: Implementations of symmetric positive definite (SPD) matrix-based neural networks for neural decoding remain fragmented across research codebases and Python packages.

By Bruno Aristimunha, Ce Ju, Antoine Collas, Florent Bouchard, Ammar Mian, Bertrand Thirion, Sylvain Chevallier, Reinmar Kobler

benchmarks

arXiv AI

Jul 7

Foundations of Equivariant Deep Learning: Unifying Graph and Sheaf Neural Networks

arXiv:2607. 03798v1 Announce Type: cross Abstract: Symmetry is everywhere in nature and society.

By Yoshihiro Maruyama

arXiv AI

Aug 12

Sheaf-Based Federated Representation Learning

arXiv:2608. 10016v1 Announce Type: cross Abstract: Heterogeneous federated systems require agents to learn and exchange informative representations despite differences in data distributions, sensing modalities, model architectures, latent dimensionalities, and local learning objectives.

By Gabriele D'Acunto, Enrico Grimaldi, Valeria Avino, Mario Edoardo Pandolfo, Leonardo Di Nino, Sergio Barbarossa, Paolo Di Lorenzo

rag agents diffusion safety

arXiv Machine Learning

Jun 16

Spectral Analysis of Molecular Features: When Richer Features Do Not Guarantee Better Generalization

arXiv:2510. 14217v2 Announce Type: replace Abstract: The spectral properties of feature embeddings offer critical insights into model generalization and representation quality.

By Asma Jamali, Tin Sum Cheng, Rodrigo A. Vargas-Hern\'andez

llms rag benchmarks

arXiv AI

Jun 3

Are Common Substructures Transferable? Riemannian Graph Foundation Model with Neural Vector Bundles

arXiv:2606. 03270v1 Announce Type: cross Abstract: Foundation models have sparked a revolution via a pretraining-adaptation paradigm, with recent efforts extending this success to graphs.

By Li Sun, Zhenhao Huang, Yiding Wang, Qin Chen, Pietro Lio, Philip S. Yu

arXiv AI

Jun 8

E2Former-V2: On-the-Fly Equivariant Attention with Linear Activation Memory

arXiv:2601. 16622v2 Announce Type: replace-cross Abstract: Equivariant Graph Neural Networks (EGNNs) have become a widely used approach for modeling 3D atomistic systems.

By Lin Huang, Chengxiang Huang, Ziang Wang, Yiyue Du, Chu Wang, Haocheng Lu, Yunyang Li, Xiaoli Liu, Arthur Jiang, Jia Zhang

llms efficiency

Related stories

SPD Learn: A Geometric Deep Learning Python Library for Neural Decoding Through Trivialization

Foundations of Equivariant Deep Learning: Unifying Graph and Sheaf Neural Networks

Sheaf-Based Federated Representation Learning

Spectral Analysis of Molecular Features: When Richer Features Do Not Guarantee Better Generalization

Are Common Substructures Transferable? Riemannian Graph Foundation Model with Neural Vector Bundles

E2Former-V2: On-the-Fly Equivariant Attention with Linear Activation Memory