arXiv Machine Learning July 30, 2026 By Martin Carrasco, Caio F. Deberaldini Netto, Vahan A. Martirosyan, Ehimare Okoyomon, Caterina Graziani

On the Rademacher Complexity of Graph Neural Networks: Unifying Expressivity and Geometry

Read the original on arXiv Machine Learning →

arXiv:2510. 10101v4 Announce Type: replace Abstract: Understanding the interplay between generalization, expressivity, and the geometry of the input space is a central challenge in graph learning.

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.

arXiv Machine Learning

Sep 1

Graph Representational Learning: When Does More Expressivity Hurt Generalization?

arXiv:2505.11298v2 Announce Type: replace Abstract: Graph Neural Networks (GNNs) are powerful tools for learning on structured data, yet the relationship between their expressivity and predictive per...

By Sohir Maskey, Raffaele Paolino, Fabian Jogl, Gitta Kutyniok, Johannes F. Lutzeyer

arXiv Machine Learning

Jul 9

Adversarial Rademacher Complexity of Deep Neural Networks

arXiv:2211. 14966v2 Announce Type: replace Abstract: Deep neural networks (DNNs) are highly vulnerable to adversarial attacks.

By Jiancong Xiao, Yanbo Fan, Ruoyu Sun, Zhi-Quan Luo

safety

arXiv AI

Aug 25

Which Algorithms Can Graph Neural Networks Learn?

arXiv:2602.13106v2 Announce Type: replace-cross Abstract: In recent years, there has been growing interest in understanding neural architectures' ability to learn to execute discrete algorithms, a li...

By Solveig Wittig, Antonis Vasileiou, Robert R. Nerem, Timo Stoll, Floris Geerts, Yusu Wang, Christopher Morris

efficiency

arXiv Machine Learning

Jun 2

Non-vacuous Generalization Bounds for Deep Neural Networks without any modification to the trained models

arXiv:2503. 07325v2 Announce Type: replace Abstract: Understanding and certifying the behavior of modern deep neural networks remains a fundamental challenge in reliable machine learning.

By Khoat Than, Dat Phan

arXiv Machine Learning

Jul 8

Deep Neural Variation Spaces: A Unifying Perspective on Depth and Complexity

arXiv:2607. 05546v1 Announce Type: cross Abstract: We develop a unified function space theory of deep fully connected neural networks.

By Julia Nakhleh, Robert D. Nowak

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

One email a morning, machine-written

Related stories

Graph Representational Learning: When Does More Expressivity Hurt Generalization?

Adversarial Rademacher Complexity of Deep Neural Networks

Which Algorithms Can Graph Neural Networks Learn?

Non-vacuous Generalization Bounds for Deep Neural Networks without any modification to the trained models

Deep Neural Variation Spaces: A Unifying Perspective on Depth and Complexity

Measuring Structure in Graph Benchmark Datasets Using Graph Invariants