English
Related papers

Related papers: Beyond Weisfeiler-Lehman: A Quantitative Framework…

200 papers

The ability of graph neural networks (GNNs) to count homomorphisms has recently been proposed as a practical and fine-grained measure of their expressive power. Although several existing works have investigated the homomorphism counting…

Machine Learning · Computer Science 2024-10-07 Junru Zhou , Muhan Zhang

While Graph Neural Networks (GNNs) have achieved remarkable results in a variety of applications, recent studies exposed important shortcomings in their ability to capture the structure of the underlying graph. It has been shown that the…

Machine Learning · Computer Science 2023-09-26 Giorgos Bouritsas , Fabrizio Frasca , Stefanos Zafeiriou , Michael M. Bronstein

Designing expressive Graph Neural Networks (GNNs) is a central topic in learning graph-structured data. While numerous approaches have been proposed to improve GNNs in terms of the Weisfeiler-Lehman (WL) test, generally there is still a…

Machine Learning · Computer Science 2024-02-13 Bohang Zhang , Shengjie Luo , Liwei Wang , Di He

Recently, subgraph GNNs have emerged as an important direction for developing expressive graph neural networks (GNNs). While numerous architectures have been proposed, so far there is still a limited understanding of how various design…

Machine Learning · Computer Science 2023-03-30 Bohang Zhang , Guhao Feng , Yiheng Du , Di He , Liwei Wang

Recently, the Weisfeiler-Lehman (WL) graph isomorphism test was used to measure the expressiveness of graph neural networks (GNNs), showing that the neighborhood aggregation GNNs were at most as powerful as 1-WL test in distinguishing graph…

Machine Learning · Computer Science 2020-12-15 Mingqi Yang , Yanming Shen , Heng Qi , Baocai Yin

Graph Neural Networks (GNN) are inherently limited in their expressive power. Recent seminal works (Xu et al., 2019; Morris et al., 2019b) introduced the Weisfeiler-Lehman (WL) hierarchy as a measure of expressive power. Although this…

Machine Learning · Computer Science 2023-06-06 Omri Puny , Derek Lim , Bobak T. Kiani , Haggai Maron , Yaron Lipman

Graph Neural Networks (GNNs) are a large class of relational models for graph processing. Recent theoretical studies on the expressive power of GNNs have focused on two issues. On the one hand, it has been proven that GNNs are as powerful…

Graph Neural Networks (GNNs) have demonstrated superior performance on various graph learning tasks, including recommendation, where they leverage user-item collaborative filtering signals in graphs. However, theoretical formulations of…

Information Retrieval · Computer Science 2023-09-19 Xuheng Cai , Lianghao Xia , Xubin Ren , Chao Huang

The expressive power of Graph Neural Networks (GNNs) has been studied extensively through the Weisfeiler-Leman (WL) graph isomorphism test. However, standard GNNs and the WL framework are inapplicable for geometric graphs embedded in…

Machine Learning · Computer Science 2024-03-05 Chaitanya K. Joshi , Cristian Bodnar , Simon V. Mathis , Taco Cohen , Pietro Liò

Graph Neural Networks (GNNs) have become the standard approach for learning and reasoning over relational data, leveraging the message-passing mechanism that iteratively propagates node embeddings through graph structures. While GNNs have…

Machine Learning · Computer Science 2025-01-14 Xiaoyu Li , Yingyu Liang , Zhenmei Shi , Zhao Song , Wei Wang , Jiahao Zhang

Research on the theoretical expressiveness of Graph Neural Networks (GNNs) has developed rapidly, and many methods have been proposed to enhance the expressiveness. However, most methods do not have a uniform expressiveness measure except…

Machine Learning · Computer Science 2024-06-04 Yanbo Wang , Muhan Zhang

Message passing graph neural networks (GNNs) are known to have their expressiveness upper-bounded by 1-dimensional Weisfeiler-Leman (1-WL) algorithm. To achieve more powerful GNNs, existing attempts either require ad hoc features, or…

Machine Learning · Computer Science 2024-01-24 Meng Liu , Haiyang Yu , Shuiwang Ji

Robustness in complex systems is of significant engineering and economic importance. However, conventional attack-based a posteriori robustness assessments incur prohibitive computational overhead. Recently, deep learning methods, such as…

Machine Learning · Computer Science 2025-12-29 Chengyu Tian , Wenbin Pei

Characterizing the separation power of graph neural networks (GNNs) provides an understanding of their limitations for graph learning tasks. Results regarding separation power are, however, usually geared at specific GNN architectures, and…

Machine Learning · Computer Science 2022-04-12 Floris Geerts , Juan L. Reutter

Graph Neural Networks (GNNs), despite achieving remarkable performance across different tasks, are theoretically bounded by the 1-Weisfeiler-Lehman test, resulting in limitations in terms of graph expressivity. Even though prior works on…

Machine Learning · Computer Science 2024-04-02 Quang Truong , Peter Chin

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…

The expressive power of Graph Neural Networks (GNNs) is often analysed via correspondence to the Weisfeiler-Leman (WL) algorithm and fragments of first-order logic. Standard GNNs are limited to performing aggregation over immediate…

Machine Learning · Computer Science 2026-02-23 Huan Luo , Jonni Virtema

Graph neural networks (GNNs) have emerged recently as a powerful architecture for learning node and graph representations. Standard GNNs have the same expressive power as the Weisfeiler-Leman test of graph isomorphism in terms of…

Machine Learning · Statistics 2020-08-11 Giannis Nikolentzos , George Dasoulas , Michalis Vazirgiannis

In recent years, Graph Neural Network (GNN) has bloomly progressed for its power in processing graph-based data. Most GNNs follow a message passing scheme, and their expressive power is mathematically limited by the discriminative ability…

Machine Learning · Computer Science 2021-04-06 Alan J. X. Guo , Qing-Hu Hou , Ou Wu

Graph neural networks (GNNs) have become the \textit{de facto} standard for representational learning in graphs, and have achieved state-of-the-art performance in many graph-related tasks; however, it has been shown that the expressive…

Machine Learning · Computer Science 2024-06-28 Tianjun Yao , Yiongxu Wang , Kun Zhang , Shangsong Liang
‹ Prev 1 2 3 10 Next ›