paper-with-me

Papers

Universal Function Approximation on Graphs

2020-03-14 · NeurIPS 2020 12 · Rickard Brüel-Gabrielsson

In this work we produce a framework for constructing universal function approximators on graph isomorphism classes. We prove how this framework comes with a collection of theoretically desirable properties and enables novel analysis. We show how this allows us to achieve state-of-the-art performance on four different well-known datasets in graph classification and separate classes of graphs that other graph-learning methods cannot. Our approach is inspired by persistent homology, dependency parsing for NLP, and multivalued functions. The complexity of the underlying algorithm is O(#edges x #nodes) and code is publicly available (https://github.com/bruel-gabrielsson/universal-function-approximation-on-graphs).

📄 PDF Abstract BibTeX arXiv:2003.06706

Code (1)

bruel-gabrielsson/universal-function-approximation-on-graphs 공식 구현 pytorch

Tasks

Dependency ParsingGraph ClassificationGraph Learning

Similar Papers 제목 키워드 기반

Belief Propagation, Bethe Approximation and Polynomials

2017-08-08 · Damian Straszak, Nisheeth K. Vishnoi

Factor graphs are important models for succinctly representing probability distributions in machine learning, coding theory, and statistical physics. Several computational problems, such as computing marginals and partit…

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

2026-02-09 · Ofek Amran, Tom Gilat, Ron Levie arxiv

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. Such analyses…

Generalization, Expressivity, and Universality of Graph Neural Networks on Attributed Graphs

2024-11-08 · 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 space of all attributed graphs that describe…

Generalization Bounds

Universality and Approximation Rates of Graph Neural Networks with Random Features

2026-07-29 · Lukas Gonon, Thilo Meyer-Brandis, Niklas Weber arxiv

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. Here, we es…

On the approximation capability of GNNs in node classification/regression tasks

2021-06-16 · Giuseppe Alessio D'Inverno, Monica Bianchini, Maria Lucia Sampoli, Franco Scarselli

Graph Neural Networks (GNNs) are a broad class of connectionist models for graph processing. Recent studies have shown that GNNs can approximate any function on graphs, modulo the equivalence relation on graphs defined b…

ClusteringGraph ClassificationNode Classificationregression