arXiv Machine Learning
Jul 30
Universality and Approximation Rates of Graph Neural Networks with Random Features
arXiv:2607. 26699v1 Announce Type: new Abstract: We investigate message-passing graph neural networks with random node features.
Universality and Approximation Rates of Graph Neural Networks with Random Features
We investigate message-passing graph neural networks with random node features. Random node features are known to enhance the expressiveness of graph neural networks (GNNs) both theoretically and empirically.
Related stories
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...
arXiv AI
Jun 8
Learning to Execute Graph Algorithms Exactly with Graph Neural Networks
arXiv:2601. 23207v2 Announce Type: replace-cross Abstract: Understanding what graph neural networks can learn, especially their ability to learn to execute algorithms, remains a central theoretical challenge.
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.
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.
arXiv Statistics ML
2d ago
Transferable Graph Metanetworks
arXiv:2610.00420v1 Announce Type: new Abstract: A weight space network (or metanetwork) takes the weights of another neural network as input and predicts properties of it. Most prior work trains such...
arXiv Machine Learning
Sep 15
Size Transferability of Graph Transformers with Convolutional Positional Encodings
arXiv:2602.15239v3 Announce Type: replace Abstract: Transformers have achieved remarkable success across domains, motivating the rise of Graph Transformers (GTs) as attention-based architectures for...
arXiv Machine Learning
Jun 30
Lost in Aggregation: On a Fundamental Expressivity Limit of Message-Passing Graph Neural Networks
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).
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.
arXiv Machine Learning
Sep 2
Why Multi-Layer Message Passing Works: Completeness Theory for Graph Neural Network Interatomic Potentials
arXiv:2609.00528v1 Announce Type: new Abstract: We prove that the Hypergraph Neural Network, an invariant architecture with 3-body message passing, is a universal approximator for potential energy su...
arXiv AI
Sep 15
Finite-Time Node Separation in Recurrent Graph Neural Networks with Persistent Gaussian Perturbations
arXiv:2609.13920v1 Announce Type: cross Abstract: Persistent Gaussian perturbations have been shown to prevent asymptotic oversmoothing in recurrent Graph Neural Networks (GNNs) by ensuring a positiv...
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...