中文
相关论文

相关论文: Global Minima, Recoverability Thresholds, and High…

200 篇论文

Graph Neural Networks (GNNs) are powerful and flexible neural networks that use the naturally sparse connectivity information of the data. GNNs represent this connectivity as sparse matrices, which have lower arithmetic intensity and thus…

机器学习 · 计算机科学 2020-09-04 Alok Tripathy , Katherine Yelick , Aydin Buluc

Scalability of graph neural networks remains one of the major challenges in graph machine learning. Since the representation of a node is computed by recursively aggregating and transforming representation vectors of its neighboring nodes…

机器学习 · 计算机科学 2021-06-10 Zengfeng Huang , Shengzhong Zhang , Chong Xi , Tang Liu , Min Zhou

Graph neural networks (GNNs) model representations from networked data and allow for decentralized inference through localized communications. Existing GNN architectures often assume ideal communications and ignore potential channel…

信号处理 · 电气工程与系统科学 2024-05-22 Zhan Gao , Deniz Gunduz

Graph Neural Networks (GNNs) are a new and increasingly popular family of deep neural network architectures to perform learning on graphs. Training them efficiently is challenging due to the irregular nature of graph data. The problem…

机器学习 · 计算机科学 2021-06-15 Marco Serafini , Hui Guan

Graph Neural Networks (GNNs) require a relatively large number of labeled nodes and a reliable/uncorrupted graph connectivity structure in order to obtain good performance on the semi-supervised node classification task. The performance of…

机器学习 · 计算机科学 2021-07-01 Abdullah Alchihabi , Yuhong Guo

In Nature Machine Intelligence 4, 367 (2022), Schuetz et al provide a scheme to employ graph neural networks (GNN) as a heuristic to solve a variety of classical, NP-hard combinatorial optimization problems. It describes how the network is…

无序系统与神经网络 · 物理学 2023-01-03 Stefan Boettcher

Graph Neural Networks (GNNs) achieve outstanding performance across graph-based tasks but remain difficult to interpret. In this paper, we revisit foundational assumptions underlying model-level explanation methods for GNNs, namely: (1)…

机器学习 · 计算机科学 2025-06-10 Hsiao-Ying Lu , Yiran Li , Ujwal Pratap Krishna Kaluvakolanu Thyagarajan , Kwan-Liu Ma

A theoretical performance analysis of the graph neural network (GNN) is presented. For classification tasks, the neural network approach has the advantage in terms of flexibility that it can be employed in a data-driven manner, whereas…

机器学习 · 计算机科学 2020-01-29 Tatsuro Kawamoto , Masashi Tsubaki , Tomoyuki Obuchi

Deep learning methods are achieving ever-increasing performance on many artificial intelligence tasks. A major limitation of deep models is that they are not amenable to interpretability. This limitation can be circumvented by developing…

机器学习 · 计算机科学 2022-07-05 Hao Yuan , Haiyang Yu , Shurui Gui , Shuiwang Ji

Graph neural networks (GNNs) have demonstrated remarkable success in graph representation learning, and various sampling approaches have been proposed to scale GNNs to applications with large-scale graphs. A class of promising GNN training…

机器学习 · 计算机科学 2024-10-10 Rui Xue , Tong Zhao , Neil Shah , Xiaorui Liu

Graph Neural Networks (GNNs) and Graph Transformers (GTs) are now a fundamental paradigm for graph learning, combining the representation-learning capabilities of deep models with the sample efficiency induced by their inductive biases.…

机器学习 · 计算机科学 2026-05-19 Stefano Carotti , Marco Pacini , Alessio Gravina , Davide Bacciu , Bruno Lepri , Sebastiano Bontorin

Graph neural networks (GNNs) have achieved tremendous success in the task of graph classification and its diverse downstream real-world applications. Despite the huge success in learning graph representations, current GNN models have…

社会与信息网络 · 计算机科学 2023-09-07 Xin Wang , Heng Chang , Beini Xie , Tian Bian , Shiji Zhou , Daixin Wang , Zhiqiang Zhang , Wenwu Zhu

Graph Neural Networks (GNNs) are characterized by their capacity of processing graph-structured data. However, due to the sparsity of labels under semi-supervised learning, they have been found to exhibit biased performance on specific…

机器学习 · 计算机科学 2025-12-16 Yihan Zhang

Graph neural networks (GNNs) achieve strong performance on graph learning tasks, but training on large-scale networks remains computationally challenging. Transferability results show that GNNs with fixed weights can generalize from smaller…

信号处理 · 电气工程与系统科学 2026-04-17 Haoyu Wang , Renyuan Ma , Gonzalo Mateos , Luana Ruiz

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

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).…

This paper derives statistical guarantees for the performance of Graph Neural Networks (GNNs) in link prediction tasks on graphs generated by a graphon. We propose a linear GNN architecture (LG-GNN) that produces consistent estimators for…

机器学习 · 计算机科学 2024-02-08 Alan Chung , Amin Saberi , Morgane Austern

Graph processes exhibit a temporal structure determined by the sequence index and and a spatial structure determined by the graph support. To learn from graph processes, an information processing architecture must then be able to exploit…

信号处理 · 电气工程与系统科学 2020-12-02 Luana Ruiz , Fernando Gama , Alejandro Ribeiro

Graph Neural Networks (GNNs) are powerful tools in representation learning for graphs. However, recent studies show that GNNs are vulnerable to carefully-crafted perturbations, called adversarial attacks. Adversarial attacks can easily fool…

机器学习 · 计算机科学 2020-06-30 Wei Jin , Yao Ma , Xiaorui Liu , Xianfeng Tang , Suhang Wang , Jiliang Tang

The performance limit of Graph Convolutional Networks (GCNs) and the fact that we cannot stack more of them to increase the performance, which we usually do for other deep learning paradigms, are pervasively thought to be caused by the…

机器学习 · 计算机科学 2023-11-07 Sitao Luan , Mingde Zhao , Xiao-Wen Chang , Doina Precup