arXiv Machine Learning June 30, 2026 By Eran Rosenbluth

Lost in Aggregation: On a Fundamental Expressivity Limit of Message-Passing Graph Neural Networks

Read the original on arXiv Machine Learning →

arXiv:2603. 14846v3 Announce Type: replace Abstract: We define an information-complexity property for aggregation functions, capturing a vast range of practical aggregations, and prove that any Message-Passing Graph Neural Network (MP-GNN) model with such aggregations induces only a polynomial number of equivalence classes on all graphs - while the number of non-isomorphic graphs is super-exponential (in number of vertices).

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

arXiv Machine Learning

Jul 30

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

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.

By Martin Carrasco, Caio F. Deberaldini Netto, Vahan A. Martirosyan, Ehimare Okoyomon, Caterina Graziani

arXiv Machine Learning

Jun 9

A Graphop Analysis of Graph Neural Networks on Sparse Graphs: Generalization and Universal Approximation

arXiv:2602. 08785v2 Announce Type: replace Abstract: Generalization and approximation capabilities of message passing graph neural networks (MPNNs) are often studied by defining a compact metric on a space of input graphs under which MPNNs are equicontinuous.

By Ofek Amran, Tom Gilat, Ron Levie

Hugging Face Trending Papers

Jun 11

Understanding Truncated Positional Encodings for Graph Neural Networks

Positional encodings (PEs) enhance the power of graph neural networks (GNNs), both theoretically and empirically. Two of the most popular families of PEs - spectral (e.

arXiv AI

Jun 2

Introduction to Graph Neural Networks for Machine Learning Engineers

arXiv:2412. 19419v2 Announce Type: replace-cross Abstract: Graph neural networks are deep neural networks designed for graphs with attributes attached to nodes or edges.

By James H. Tanis, Chris Giannella, Adrian V. Mariano, Daoud Meerzaman

arXiv Machine Learning

Jun 17

Weisfeiler Lehman Test on Combinatorial Complexes: Generalized Expressive Power of Topological Neural Networks

arXiv:2605. 00725v2 Announce Type: replace Abstract: Topological neural networks have emerged as effective tools for modeling higher-order relational structures beyond pairwise graphs, including hypergraphs, simplicial complexes, and cell complexes.

By Jiawen Chen, Qi Shao, Zhiqiang Ge, Duxin Chen, Wenwu Yu

benchmarks

arXiv Machine Learning

Jul 30

Automorphism-Induced Non-Canonicity in Top-k Explanations of Graph Neural Networks

arXiv:2607. 26344v1 Announce Type: new Abstract: A gradient-based GNN explainer given a molecule with two chemically equivalent nitro groups assigns them attribution scores that are equal to the last bit.

By Xin Xu, Siru Tao, Kaizhen Tan

efficiency

Related stories

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

A Graphop Analysis of Graph Neural Networks on Sparse Graphs: Generalization and Universal Approximation

Understanding Truncated Positional Encodings for Graph Neural Networks

Introduction to Graph Neural Networks for Machine Learning Engineers

Weisfeiler Lehman Test on Combinatorial Complexes: Generalized Expressive Power of Topological Neural Networks

Automorphism-Induced Non-Canonicity in Top-k Explanations of Graph Neural Networks