8 papers
Adaptive Canonicalization with Application to Invariant Anisotropic Geometric Networks
Ya-Wei Eileen Lin, Ron Levie
Canonicalization is a widely used strategy in equivariant machine learning, enforcing symmetry in neural networks by mapping each input to a standard form. Yet, it often introduces…
A Note on Graphon-Signal Analysis of Graph Neural Networks
Levi Rauchwerger, Ron Levie
A recent paper, ``A Graphon-Signal Analysis of Graph Neural Networks'', by Levie, analyzed message passing graph neural networks (MPNNs) by embedding the input space of MPNNs, i.e.…
Equivariance Everywhere All At Once: A Recipe for Graph Foundation Models
Ben Finkelshtein, İsmail İlkan Ceylan, Michael Bronstein +1
Graph machine learning architectures are typically tailored to specific tasks on specific datasets, which hinders their broader applicability. This has led to a new quest in graph…
Efficient Learning on Large Graphs using a Densifying Regularity Lemma
Jonathan Kouchly, Ben Finkelshtein, Michael Bronstein +1
Learning on large graphs presents significant challenges, with traditional Message Passing Neural Networks suffering from computational and memory costs scaling linearly with the n…
Survey on Generalization Theory for Graph Neural Networks
Antonis Vasileiou, Stefanie Jegelka, Ron Levie +1
Message-passing graph neural networks (MPNNs) have emerged as the leading approach for machine learning on graphs, attracting significant attention in recent years. While a large s…
Covered Forest: Fine-grained generalization analysis of graph neural networks
Antonis Vasileiou, Ben Finkelshtein, Floris Geerts +2
The expressive power of message-passing graph neural networks (MPNNs) is reasonably well understood, primarily through combinatorial techniques from graph isomorphism testing. Howe…
Generalization, Expressivity, and Universality of Graph Neural Networks on Attributed Graphs
Levi Rauchwerger, Stefanie Jegelka, Ron Levie
We analyze the universality and generalization of graph neural networks (GNNs) on attributed graphs, i.e., with node attributes. To this end, we propose pseudometrics over the spac…
PieClam: A Universal Graph Autoencoder Based on Overlapping Inclusive and Exclusive Communities
Daniel Zilberg, Ron Levie
We propose PieClam (Prior Inclusive Exclusive Cluster Affiliation Model): a probabilistic graph model for representing any graph as overlapping generalized communities. Our method…