中文
相关论文

相关论文: On The Expressive Power of GNN Derivatives

200 篇论文

Graph neural networks (GNNs) can effectively model structural information of graphs, making them widely used in knowledge graph (KG) reasoning. However, existing studies on the expressive power of GNNs mainly focuses on simple…

人工智能 · 计算机科学 2026-02-02 Han Yu , Xiaojuan Zhao , Aiping Li , Kai Chen , Ziniu Liu , Zhichao Peng

The study of Graph Neural Networks has received considerable interest in the past few years. By extending deep learning to graph-structured data, GNNs can solve a diverse set of tasks in fields including social science, chemistry, and…

机器学习 · 计算机科学 2024-03-12 Ashwin Nalwade , Kelly Marshall , Axel Eladi , Umang Sharma

Graph neural network (GNN) is effective to model graphs for distributed representations of nodes and an entire graph. Recently, research on the expressive power of GNN attracted growing attention. A highly-expressive GNN has the ability to…

机器学习 · 计算机科学 2022-03-01 Chengsheng Mao , Yuan Luo

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.…

机器学习 · 计算机科学 2025-01-13 Bingxu Zhang , Changjun Fan , Shixuan Liu , Kuihua Huang , Xiang Zhao , Jincai Huang , Zhong Liu

Graphs can model complicated interactions between entities, which naturally emerge in many important applications. These applications can often be cast into standard graph learning tasks, in which a crucial step is to learn low-dimensional…

机器学习 · 计算机科学 2023-07-04 Xuexin Chen , Ruichu Cai , Yuan Fang , Min Wu , Zijian Li , Zhifeng Hao

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…

机器学习 · 计算机科学 2024-06-28 Tianjun Yao , Yiongxu Wang , Kun Zhang , Shangsong Liang

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…

计算机科学中的逻辑 · 计算机科学 2026-01-30 Arie Soeteman , Michael Benedikt , Martin Grohe , Balder ten Cate

Message-passing graph neural networks (MPNNs) emerged as powerful tools for processing graph-structured input. However, they operate on a fixed input graph structure, ignoring potential noise and missing information. Furthermore, their…

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…

机器学习 · 计算机科学 2024-02-13 Bohang Zhang , Shengjie Luo , Liwei Wang , Di He

Message passing neural networks (MPNNs) have become a dominant flavor of graph neural networks (GNNs) in recent years. Yet, MPNNs come with notable limitations; namely, they are at most as powerful as the 1-dimensional Weisfeiler-Leman…

机器学习 · 计算机科学 2022-11-04 Lingxiao Zhao , Louis Härtel , Neil Shah , Leman Akoglu

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…

机器学习 · 计算机科学 2023-06-06 Omri Puny , Derek Lim , Bobak T. Kiani , Haggai Maron , Yaron Lipman

Subgraph-enhanced graph neural networks (SGNN) can increase the expressive power of the standard message-passing framework. This model family represents each graph as a collection of subgraphs, generally extracted by random sampling or with…

机器学习 · 计算机科学 2023-04-17 Indro Spinelli , Michele Guerra , Filippo Maria Bianchi , Simone Scardapane

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…

机器学习 · 计算机科学 2021-01-07 Kenta Oono , Taiji Suzuki

We perform the first adversarial robustness study into Graph Neural Networks (GNNs) that are provably more powerful than traditional Message Passing Neural Networks (MPNNs). In particular, we use adversarial robustness as a tool to uncover…

机器学习 · 计算机科学 2024-07-04 Francesco Campi , Lukas Gosch , Tom Wollschläger , Yan Scholten , Stephan Günnemann

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…

机器学习 · 计算机科学 2024-06-07 Bohang Zhang , Lingxiao Zhao , Haggai Maron

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,…

机器学习 · 计算机科学 2024-10-15 Shouheng Li , Floris Geerts , Dongwoo Kim , Qing Wang

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…

机器学习 · 计算机科学 2020-10-19 Ryoma Sato

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…

机器学习 · 计算机科学 2021-06-08 Waïss Azizian , Marc Lelarge

Higher-order features bring significant accuracy gains in semantic dependency parsing. However, modeling higher-order features with exact inference is NP-hard. Graph neural networks (GNNs) have been demonstrated to be an effective tool for…

计算与语言 · 计算机科学 2022-01-28 Bin Li , Yunlong Fan , Yikemaiti Sataer , Zhiqiang Gao

Graph neural networks (GNN) are deep learning architectures for graphs. Essentially, a GNN is a distributed message passing algorithm, which is controlled by parameters learned from data. It operates on the vertices of a graph: in each…

计算机科学中的逻辑 · 计算机科学 2024-05-21 Martin Grohe , Eran Rosenbluth
‹ 上一页 1 2 3 10 下一页 ›