English
Related papers

Related papers: A Practical, Progressively-Expressive GNN

200 papers

Various classes of Graph Neural Networks (GNN) have been proposed and shown to be successful in a wide range of applications with graph structured data. In this paper, we propose a theoretical framework able to compare the expressive power…

Machine Learning · Computer Science 2021-06-08 Waïss Azizian , Marc Lelarge

Graph neural networks (GNNs) are deep learning architectures for machine learning problems on graphs. It has recently been shown that the expressiveness of GNNs can be characterised precisely by the combinatorial Weisfeiler-Leman algorithms…

Machine Learning · Computer Science 2022-01-11 Martin Grohe

Expressivity and generalization are two critical aspects of graph neural networks (GNNs). While significant progress has been made in studying the expressivity of GNNs, much less is known about their generalization capabilities,…

Machine Learning · Computer Science 2024-10-15 Shouheng Li , Floris Geerts , Dongwoo Kim , Qing Wang

Developing models that can learn to reason is a notoriously challenging problem. We focus on reasoning in relational domains, where the use of Graph Neural Networks (GNNs) seems like a natural choice. However, previous work has shown that…

Artificial Intelligence · Computer Science 2025-03-03 Irtaza Khalid , Steven Schockaert

Graph neural networks (GNNs) are effective models for representation learning on relational data. However, standard GNNs are limited in their expressive power, as they cannot distinguish graphs beyond the capability of the Weisfeiler-Leman…

Machine Learning · Computer Science 2021-06-07 Ralph Abboud , İsmail İlkan Ceylan , Martin Grohe , Thomas Lukasiewicz

Incorporating spectral information to enhance Graph Neural Networks (GNNs) has shown promising results but raises a fundamental challenge due to the inherent ambiguity of eigenvectors. Various architectures have been proposed to address…

Machine Learning · Computer Science 2024-06-07 Bohang Zhang , Lingxiao Zhao , Haggai Maron

Graph data is omnipresent and has a wide variety of applications, such as in natural science, social networks, or the semantic web. However, while being rich in information, graphs are often noisy and incomplete. As a result, graph…

Artificial Intelligence · Computer Science 2023-09-01 Luisa Werner , Nabil Layaïda , Pierre Genevès , Sarah Chlyah

Graph Neural Networks (GNNs) have recently been used for node and graph classification tasks with great success, but GNNs model dependencies among the attributes of nearby neighboring nodes rather than dependencies among observed node…

Machine Learning · Computer Science 2020-09-30 Mengyue Hang , Jennifer Neville , Bruno Ribeiro

Subgraph GNNs are provably expressive neural architectures that learn graph representations from sets of subgraphs. Unfortunately, their applicability is hampered by the computational complexity associated with performing message passing on…

Machine Learning · Computer Science 2024-03-22 Beatrice Bevilacqua , Moshe Eliasof , Eli Meirom , Bruno Ribeiro , Haggai Maron

Expressivity theory, characterizing which graphs a GNN can distinguish, has become the predominant framework for analyzing GNNs, with new models striving for higher expressivity. However, we argue that this focus is misguided: First, higher…

Machine Learning · Computer Science 2025-10-23 Niklas Kemper , Tom Wollschläger , Stephan Günnemann

Constructing appropriate representations of molecules lies at the core of numerous tasks such as material science, chemistry and drug designs. Recent researches abstract molecules as attributed graphs and employ graph neural networks (GNN)…

Machine Learning · Computer Science 2021-07-29 Jianwen Chen , Shuangjia Zheng , Ying Song , Jiahua Rao , Yuedong Yang

Graph Neural Networks (GNNs) are learning models aimed at processing graphs and signals on graphs. The most popular and successful GNNs are based on message passing schemes. Such schemes inherently have limited expressive power when it…

Machine Learning · Computer Science 2022-06-24 Jacob Bamberger

Graph kernels based on the $1$-dimensional Weisfeiler-Leman algorithm and corresponding neural architectures recently emerged as powerful tools for (supervised) learning with graphs. However, due to the purely local nature of the…

Data Structures and Algorithms · Computer Science 2020-10-20 Christopher Morris , Gaurav Rattan , Petra Mutzel

Graph transformers have recently received significant attention in graph learning, partly due to their ability to capture more global interaction via self-attention. Nevertheless, while higher-order graph neural networks have been…

Machine Learning · Computer Science 2024-04-05 Cai Zhou , Rose Yu , Yusu Wang

Graph Neural Networks (GNNs) have emerged as a powerful tool for data-driven learning on various graph domains. They are usually based on a message-passing mechanism and have gained increasing popularity for their intuitive formulation,…

Machine Learning · Computer Science 2023-11-02 Giuseppe Alessio D'Inverno , Simone Brugiapaglia , Mirco Ravanelli

Learning representations of sets of nodes in a graph is crucial for applications ranging from node-role discovery to link prediction and molecule classification. Graph Neural Networks (GNNs) have achieved great success in graph…

Machine Learning · Computer Science 2020-10-30 Pan Li , Yanbang Wang , Hongwei Wang , Jure Leskovec

While Graph Neural Networks (GNNs) are powerful models for learning representations on graphs, most state-of-the-art models do not have significant accuracy gain beyond two to three layers. Deep GNNs fundamentally need to address: 1).…

Graphs are ubiquitous in real-world applications, ranging from social networks to biological systems, and have inspired the development of Graph Neural Networks (GNNs) for learning expressive representations. While most research has…

Random walk neural networks (RWNNs) have emerged as a promising approach for graph representation learning, leveraging recent advances in sequence models to process random walks. However, under realistic sampling constraints, RWNNs often…

Machine Learning · Computer Science 2025-10-28 Michael Ito , Danai Koutra , Jenna Wiens

Graph Neural Networks (GNNs) have become the state-of-the-art method for many applications on graph structured data. GNNs are a model for graph representation learning, which aims at learning to generate low dimensional node embeddings that…

Machine Learning · Computer Science 2022-05-23 Davide Buffelli , Fabio Vandin