English
Related papers

Related papers: WL meet VC

200 papers

Graph Neural Networks (GNNs) are powerful tools for learning on structured data, yet the relationship between their expressivity and predictive performance remains unclear. We introduce a family of premetrics that capture different degrees…

Machine Learning · Computer Science 2025-05-19 Sohir Maskey , Raffaele Paolino , Fabian Jogl , Gitta Kutyniok , Johannes F. Lutzeyer

The graph coloring problem asks for an assignment of the minimum number of distinct colors to vertices in an undirected graph with the constraint that no pair of adjacent vertices share the same color. The problem is a thoroughly studied…

Machine Learning · Computer Science 2024-08-12 Kenneth Langedal , Fredrik Manne

Inspired by convolutional neural networks on 1D and 2D data, graph convolutional neural networks (GCNNs) have been developed for various learning tasks on graph data, and have shown superior performance on real-world datasets. Despite their…

Machine Learning · Computer Science 2019-05-15 Saurabh Verma , Zhi-Li Zhang

Graph neural networks (GNNs) are a widely used class of machine learning models for graph-structured data, based on local aggregation over neighbors. GNNs have close connections to logic. In particular, their expressive power is linked to…

Logic in Computer Science · Computer Science 2026-01-30 Arie Soeteman , Michael Benedikt , Martin Grohe , Balder ten Cate

We address two fundamental questions about graph neural networks (GNNs). First, we prove that several important graph properties cannot be computed by GNNs that rely entirely on local information. Such GNNs include the standard message…

Machine Learning · Computer Science 2020-02-17 Vikas K. Garg , Stefanie Jegelka , Tommi Jaakkola

The Vapnik-Chervonenkis dimension (in short, VC-dimension) of a graph is defined as the VC-dimension of the set system induced by the neighborhoods of its vertices. We show that every $n$-vertex graph with bounded VC-dimension contains a…

Combinatorics · Mathematics 2017-10-11 Jacob Fox , János Pach , Andrew Suk

The application of deep learning to symbolic domains remains an active research endeavour. Graph neural networks (GNN), consisting of trained neural modules which can be arranged in different topologies at run time, are sound alternatives…

Social and Information Networks · Computer Science 2019-12-02 Pedro H. C. Avelar , Henrique Lemos , Marcelo O. R. Prates , Luis Lamb

Graph neural networks (GNN) are very popular methods in machine learning and have been applied very successfully to the prediction of the properties of molecules and materials. First-order GNNs are well known to be incomplete, i.e., there…

Machine Learning · Statistics 2022-11-08 Sergey N. Pozdnyakov , Michele Ceriotti

In comparison to graphs, combinatorial methods for the isomorphism problem of finite groups are less developed than algebraic ones. To be able to investigate the descriptive complexity of finite groups and the group isomorphism problem, we…

Logic in Computer Science · Computer Science 2021-11-24 Jendrik Brachter , Pascal Schweitzer

Graph neural networks are widely used tools for graph prediction tasks. Motivated by their empirical performance, prior works have developed generalization bounds for graph neural networks, which scale with graph structures in terms of the…

Machine Learning · Computer Science 2023-10-25 Haotian Ju , Dongyue Li , Aneesh Sharma , Hongyang R. Zhang

Although graph neural networks (GNNs) have made great progress recently on learning from graph-structured data in practice, their theoretical guarantee on generalizability remains elusive in the literature. In this paper, we provide a…

Machine Learning · Computer Science 2020-06-26 Shuai Zhang , Meng Wang , Sijia Liu , Pin-Yu Chen , Jinjun Xiong

In this paper, we study the generalization capabilities of geometric graph neural networks (GNNs). We consider GNNs over a geometric graph constructed from a finite set of randomly sampled points over an embedded manifold with topological…

Signal Processing · Electrical Eng. & Systems 2025-06-10 Zhiyang Wang , Juan Cervino , Alejandro Ribeiro

Graph neural networks (GNNs) are widely used in graph learning and most architectures propagate information by passing messages between vertices. In this work, we shift our attention to GNNs that perform message passing on edges and…

Machine Learning · Computer Science 2026-02-03 Pablo Barceló , Fabian Jogl , Alexander Kozachinskiy , Matthias Lanzinger , Stefan Neumann , Cristóbal Rojas

Message-passing neural networks (MPNNs) are the leading architecture for deep learning on graph-structured data, in large part due to their simplicity and scalability. Unfortunately, it was shown that these architectures are limited in…

Graph Neural Networks (GNNs) are a popular approach for predicting graph structured data. As GNNs tightly entangle the input graph into the neural network structure, common explainable AI approaches are not applicable. To a large extent,…

Let $G = (V,E)$ be a graph, and for each $e \in E(G)$, let $L_e$ be a list of real numbers. Let $w:E(G) \to \cup_{e \in E(G)}L_e$ be an edge weighting function such that $w(e) \in L_e$ for each $e \in E(G)$, and let $c_w$ be the vertex…

Combinatorics · Mathematics 2014-01-28 Ben Seamone

Graph neural networks (GNNs) have become compelling models designed to perform learning and inference on graph-structured data. However, little work has been done to understand the fundamental limitations of GNNs for scaling to larger…

Machine Learning · Computer Science 2023-10-27 Hyungeun Lee , Kijung Yoon

Graph Neural Networks (GNNs) face fundamental limitations in expressivity and capturing structural heterogeneity. Standard message-passing architectures are constrained by the 1-dimensional Weisfeiler-Leman (1-WL) test, unable to…

Machine Learning · Computer Science 2026-05-19 Asela Hevapathige , Ahad N. Zehmakan , Asiri Wijesinghe , Saman Halgamuge

Famously, the ability of Message Passing Neural Networks (MPNN) to distinguish between graphs is limited to graphs separable by the Weisfeiler-Lemann (WL) graph isomorphism test, and the strongest MPNNs, in terms of separation power, are…

Machine Learning · Computer Science 2026-03-03 Yonatan Sverdlov , Yair Davidson , Nadav Dym , Tal Amir

In recent years, algorithms and neural architectures based on the Weisfeiler--Leman algorithm, a well-known heuristic for the graph isomorphism problem, have emerged as a powerful tool for machine learning with graphs and relational data.…