English
Related papers

Related papers: Equivariant Polynomials for Graph Neural Networks

200 papers

Graph Neural Networks (graph NNs) are a promising deep learning approach for analyzing graph-structured data. However, it is known that they do not improve (or sometimes worsen) their predictive performance as we pile up many layers and add…

Machine Learning · Computer Science 2021-01-07 Kenta Oono , Taiji Suzuki

Graph Neural Networks (GNNs) are effective tools for graph representation learning. Most GNNs rely on a recursive neighborhood aggregation scheme, named message passing, thereby their theoretical expressive power is limited to the…

Machine Learning · Computer Science 2023-09-19 Dingmin Wang , Shengchao Liu , Hanchen Wang , Bernardo Cuenca Grau , Linfeng Song , Jian Tang , Song Le , Qi Liu

Spectral features are widely incorporated within Graph Neural Networks (GNNs) to improve their expressive power, or their ability to distinguish among non-isomorphic graphs. One popular example is the usage of graph Laplacian eigenvectors…

Machine Learning · Computer Science 2025-09-29 Snir Hordan , Maya Bechler-Speicher , Gur Lifshitz , Nadav Dym

Numerous recent works have analyzed the expressive power of message-passing graph neural networks (MPNNs), primarily utilizing combinatorial techniques such as the $1$-dimensional Weisfeiler-Leman test ($1$-WL) for the graph isomorphism…

Machine Learning · Computer Science 2023-11-03 Jan Böker , Ron Levie , Ningyuan Huang , Soledad Villar , Christopher Morris

Knowledge graphs, modeling multi-relational data, improve numerous applications such as question answering or graph logical reasoning. Many graph neural networks for such data emerged recently, often outperforming shallow architectures.…

Machine Learning · Computer Science 2022-12-01 Pablo Barcelo , Mikhail Galkin , Christopher Morris , Miguel Romero Orth

Graph neural networks (GNNs) are effective machine learning models for many graph-related applications. Despite their empirical success, many research efforts focus on the theoretical limitations of GNNs, i.e., the GNNs expressive power.…

Machine Learning · Computer Science 2025-01-13 Bingxu Zhang , Changjun Fan , Shixuan Liu , Kuihua Huang , Xiang Zhao , Jincai Huang , Zhong Liu

Graph Neural Networks (GNN) come in many flavors, but should always be either invariant (permutation of the nodes of the input graph does not affect the output) or equivariant (permutation of the input permutes the output). In this paper,…

Machine Learning · Computer Science 2019-10-25 Nicolas Keriven , Gabriel Peyré

Numerous subgraph-enhanced graph neural networks (GNNs) have emerged recently, provably boosting the expressive power of standard (message-passing) GNNs. However, there is a limited understanding of how these approaches relate to each other…

Machine Learning · Computer Science 2022-10-18 Chendi Qian , Gaurav Rattan , Floris Geerts , Christopher Morris , Mathias Niepert

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

Graph neural networks (GNNs) are effective machine learning models for various graph learning problems. Despite their empirical successes, the theoretical limitations of GNNs have been revealed recently. Consequently, many GNN models have…

Machine Learning · Computer Science 2020-10-19 Ryoma Sato

We propose a Graph Neural Network with greater expressive power than commonly used GNNs - not constrained to only differentiate between graphs that Weisfeiler-Lehman test recognizes to be non-isomorphic. We use a graph attention network…

Machine Learning · Computer Science 2020-04-14 Stanisław Purgał

The Weisfeiler-Leman algorithm ($1$-WL) is a well-studied heuristic for the graph isomorphism problem. Recently, the algorithm has played a prominent role in understanding the expressive power of message-passing graph neural networks…

Machine Learning · Computer Science 2024-05-29 Billy J. Franks , Christopher Morris , Ameya Velingker , Floris Geerts

Graph neural network (GNN)'s success in graph classification is closely related to the Weisfeiler-Lehman (1-WL) algorithm. By iteratively aggregating neighboring node features to a center node, both 1-WL and GNN obtain a node representation…

Machine Learning · Computer Science 2021-10-27 Muhan Zhang , Pan Li

Many problems in computer vision and machine learning can be cast as learning on hypergraphs that represent higher-order relations. Recent approaches for hypergraph learning extend graph neural networks based on message passing, which is…

Machine Learning · Computer Science 2022-08-23 Jinwoo Kim , Saeyoon Oh , Sungjun Cho , Seunghoon Hong

Graph Neural Networks (GNNs) show strong expressive power on graph data mining, by aggregating information from neighbors and using the integrated representation in the downstream tasks. The same aggregation methods and parameters for each…

Machine Learning · Computer Science 2022-03-22 Xiaojun Ma , Qin Chen , Yuanyi Ren , Guojie Song , Liang Wang

Recently, many works studied the expressive power of graph neural networks (GNNs) by linking it to the $1$-dimensional Weisfeiler--Leman algorithm ($1\text{-}\mathsf{WL}$). Here, the $1\text{-}\mathsf{WL}$ is a well-studied heuristic for…

Machine Learning · Computer Science 2023-05-31 Christopher Morris , Floris Geerts , Jan Tönshoff , Martin Grohe

Graph neural networks (GNNs) have limited expressive power, failing to represent many graph classes correctly. While more expressive graph representation learning (GRL) alternatives can distinguish some of these classes, they are…

Machine Learning · Computer Science 2021-12-08 Leonardo Cotta , Christopher Morris , Bruno Ribeiro

In recent years, there has been a significant amount of research focused on expanding the expressivity of Graph Neural Networks (GNNs) beyond the Weisfeiler-Lehman (1-WL) framework. While many of these studies have yielded advancements in…

Machine Learning · Computer Science 2024-03-12 Shouheng Li , Dongwoo Kim , Qing Wang

The expressive power of graph neural networks (GNNs) is typically understood through their correspondence with graph isomorphism tests such as the Weisfeiler-Leman (WL) hierarchy. While more expressive GNNs can distinguish a richer set of…

Relational pooling is a framework for building more expressive and permutation-invariant graph neural networks. However, there is limited understanding of the exact enhancement in the expressivity of RP and its connection with the…

Machine Learning · Computer Science 2023-05-10 Cai Zhou , Xiyuan Wang , Muhan Zhang