arXiv Machine Learning June 5, 2026 By Michael Murray, Tenzin Chan, Kedar Karhadker, Christopher J. Hillar

Implicit Bias and Invariance: How Hopfield Networks Efficiently Learn Graph Orbits

Read the original on arXiv Machine Learning →

arXiv:2512. 14338v3 Announce Type: replace Abstract: Many learning problems involve symmetries, and while invariance can be built into neural architectures, it can also emerge implicitly when training on group-structured data.

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.

safety

arXiv Machine Learning

2d ago

Measuring Structure in Graph Benchmark Datasets Using Graph Invariants

arXiv:2605.06462v2 Announce Type: replace Abstract: Progress in graph learning is hindered by benchmark practices that conflate the contributions of node features and graph structure, making it hard...

By Richard von Moos, Mathieu Alain, Bastian Rieck

llms benchmarks

arXiv Machine Learning

Sep 10

Efficient Learning and Symmetry Discovery under Exact Invariances

arXiv:2609.07031v1 Announce Type: new Abstract: Learning with group invariances is central to many scientific and geometric learning problems, yet its computational foundations remain poorly understo...

By Ashkan Soleymani, Behrooz Tahmasebi, Patrick Jaillet, Stefanie Jegelka

arXiv Machine Learning

Sep 10

Topology-induced Operators Reveal Complementary Graph Representations without Training

arXiv:2609.08152v1 Announce Type: new Abstract: Graph representation learning has largely focused on designing increasingly sophisticated models to transform graph topology into vector representation...

By Meng Qin, Jinqiang Cui, Hongwei Zheng, Weihua Li, Sen Pei

rag

Hugging Face Trending Papers

Sep 8

Topology-induced Operators Reveal Complementary Graph Representations without Training

The paper demonstrates that high‑quality graph embeddings can be produced without complex models or training by propagating random features through topological structures derived from random walks and anonymous walks. These training‑free embeddings capture node proximity and structural roles, respectively, and perform competitively on node, edge, and graph tasks while often requiring less computation. Combining the two embedding types further improves inference quality for some tasks.

rag

arXiv Machine Learning

Jun 2

Network Learning with Semi-relaxed Gromov-Wasserstein

arXiv:2606. 02223v1 Announce Type: new Abstract: Estimating the generative mechanism of large-scale networks is a fundamental challenge in statistical machine learning.

By Charles Dufour, Ulysse Naepels, Leonardo V. Santoro

arXiv Machine Learning

Jun 2

Towards Stable, Globally Expressive Graph Representations with Laplacian Eigenvectors

arXiv:2410. 09737v2 Announce Type: replace Abstract: A popular way to improve the expressive power of graph neural networks (GNNs) is to use Laplacian eigenvectors as additional node features, since they can serve both as structural identifiers and global coordinates of nodes.

By Junru Zhou, Cai Zhou, Xiyuan Wang, Pan Li, Muhan Zhang

benchmarks

One email a morning, machine-written

Related stories

Measuring Structure in Graph Benchmark Datasets Using Graph Invariants

Efficient Learning and Symmetry Discovery under Exact Invariances

Topology-induced Operators Reveal Complementary Graph Representations without Training

Topology-induced Operators Reveal Complementary Graph Representations without Training

Network Learning with Semi-relaxed Gromov-Wasserstein

Towards Stable, Globally Expressive Graph Representations with Laplacian Eigenvectors