中文
相关论文

相关论文: Universality of Group Convolutional Neural Network…

200 篇论文

$G$-equivariant convolutional neural networks (GCNNs) is a geometric deep learning model for data defined on a homogeneous $G$-space $\mathcal{M}$. GCNNs are designed to respect the global symmetry in $\mathcal{M}$, thereby facilitating…

机器学习 · 计算机科学 2022-07-27 Jimmy Aronsson

Graph Neural Networks (GNNs) have emerged as formidable resources for processing graph-based information across diverse applications. While the expressive power of GNNs has traditionally been examined in the context of graph-level tasks,…

机器学习 · 计算机科学 2025-03-12 A. Martina Neuman , Rongrong Wang , Yuying Xie

Group equivariant convolutional neural networks (G-CNNs) are generalizations of convolutional neural networks (CNNs) which excel in a wide range of technical applications by explicitly encoding symmetries, such as rotations and…

机器学习 · 计算机科学 2022-09-14 Hannah Lawrence , Kristian Georgiev , Andrew Dienes , Bobak T. Kiani

This paper builds on the connection between graph neural networks and traditional dynamical systems. We propose continuous graph neural networks (CGNN), which generalise existing graph neural networks with discrete dynamics in that they can…

机器学习 · 计算机科学 2020-07-17 Louis-Pascal A. C. Xhonneux , Meng Qu , Jian Tang

Depth estimation is a challenging task of 3D reconstruction to enhance the accuracy sensing of environment awareness. This work brings a new solution with a set of improvements, which increase the quantitative and qualitative understanding…

计算机视觉与模式识别 · 计算机科学 2021-12-14 Armin Masoumian , Hatem A. Rashwan , Saddam Abdulwahab , Julian Cristiano , Domenec Puig

Two architectures that generalize convolutional neural networks (CNNs) for the processing of signals supported on graphs are introduced. We start with the selection graph neural network (GNN), which replaces linear time invariant filters…

信号处理 · 电气工程与系统科学 2019-01-30 Fernando Gama , Antonio G. Marques , Geert Leus , Alejandro Ribeiro

Graph neural networks (GNNs) have become a core paradigm for learning on relational data. In materials science, equivariant GNNs (EGNNs) have emerged as a compelling backbone for crystalline-structure prediction, owing to their ability to…

机器学习 · 计算机科学 2025-10-08 Yang Cao , Zhao Song , Jiahao Zhang , Jiale Zhao

We develop a theory of category-equivariant neural networks (CENNs) that unifies group/groupoid-equivariant networks, poset/lattice-equivariant networks, graph and sheaf neural networks. Equivariance is formulated as naturality in a…

机器学习 · 计算机科学 2025-12-24 Yoshihiro Maruyama

Graph neural networks (GNNs) provide state-of-the-art results in a wide variety of tasks which typically involve predicting features at the vertices of a graph. They are built from layers of graph convolutions which serve as a powerful…

机器学习 · 统计学 2024-11-08 Mauricio Velasco , Kaiying O'Hare , Bernardo Rychtenberg , Soledad Villar

Important advances have been made using convolutional neural network (CNN) approaches to solve complicated problems in areas that rely on grid structured data such as image processing and object classification. Recently, research on graph…

机器学习 · 统计学 2018-08-24 Matthew Baron

Recently proposed Gated Linear Networks present a tractable nonlinear network architecture, and exhibit interesting capabilities such as learning with local error signals and reduced forgetting in sequential learning. In this work, we…

机器学习 · 计算机科学 2022-12-13 Qianyi Li , Haim Sompolinsky

Graph Neural Networks (GNNs) are a promising deep learning approach for circumventing many real-world problems on graph-structured data. However, these models usually have at least one of four fundamental limitations: over-smoothing,…

机器学习 · 计算机科学 2022-10-03 Xun Liu , Alex Hay-Man Ng , Fangyuan Lei , Yikuan Zhang , Zhengmin Li

Graph neural networks (GNNs) demonstrate a robust capability for representation learning on graphs with complex structures, showcasing superior performance in various applications. The majority of existing GNNs employ a graph convolution…

机器学习 · 计算机科学 2025-02-19 Jinlu Wang , Jipeng Guo , Yanfeng Sun , Junbin Gao , Shaofan Wang , Yachao Yang , Baocai Yin

This paper reviews graph convolutional neural networks (GCNNs) through the lens of edge-variant graph filters. The edge-variant graph filter is a finite order, linear, and local recursion that allows each node, in each iteration, to weigh…

机器学习 · 计算机科学 2019-03-05 Elvin Isufi , Fernando Gama , Alejandro Ribeiro

We present our ongoing work on understanding the limitations of graph convolutional networks (GCNs) as well as our work on generalizations of graph convolutions for representing more complex node attribute dependencies. Based on an analysis…

机器学习 · 计算机科学 2018-05-07 Mathias Niepert , Alberto Garcia-Duran

We define the bicategory of Graph Convolutional Neural Networks $\mathbf{GCNN}_n$ for an arbitrary graph with $n$ nodes. We show it can be factored through the already existing categorical constructions for deep learning called…

范畴论 · 数学 2022-12-02 Bruno Gavranović , Mattia Villani

Message-passing neural networks (MPNNs) have been successfully applied to representation learning on graphs in a variety of real-world applications. However, two fundamental weaknesses of MPNNs' aggregators limit their ability to represent…

机器学习 · 计算机科学 2020-02-17 Hongbin Pei , Bingzhe Wei , Kevin Chen-Chuan Chang , Yu Lei , Bo Yang

We introduce a general method for achieving robust group-invariance in group-equivariant convolutional neural networks ($G$-CNNs), which we call the $G$-triple-correlation ($G$-TC) layer. The approach leverages the theory of the…

机器学习 · 计算机科学 2024-01-29 Sophia Sanborn , Nina Miolane

Deep Learning methods, specifically convolutional neural networks (CNNs), have seen a lot of success in the domain of image-based data, where the data offers a clearly structured topology in the regular lattice of pixels. This…

机器学习 · 统计学 2018-05-31 Thomas Teh , Chaiyawan Auepanwiriyakul , John Alexander Harston , A. Aldo Faisal

The human brain has an inherent ability to fill in gaps to perceive figures as complete wholes, even when parts are missing or fragmented. This phenomenon is known as Closure in psychology, one of the Gestalt laws of perceptual…

计算机视觉与模式识别 · 计算机科学 2025-07-10 Yuyan Zhang , Derya Soydaner , Lisa Koßmann , Fatemeh Behrad , Johan Wagemans