中文
相关论文

相关论文: Rotation-equivariant Graph Neural Networks for Lea…

200 篇论文

Graph Neural Networks (GNNs) have established themselves as a key component in addressing diverse graph-based tasks. Despite their notable successes, GNNs remain susceptible to input perturbations in the form of adversarial attacks. This…

机器学习 · 计算机科学 2024-09-13 Moshe Eliasof , Davide Murari , Ferdia Sherry , Carola-Bibiane Schönlieb

Graph Neural Networks (GNNs) are a form of deep learning that enable a wide range of machine learning applications on graph-structured data. The learning of GNNs, however, is known to pose challenges for memory-constrained devices such as…

机器学习 · 计算机科学 2023-05-01 Jeroen Bollen , Jasper Steegmans , Jan Van den Bussche , Stijn Vansummeren

A reliable perception has to be robust against challenging environmental conditions. Therefore, recent efforts focused on the use of radar sensors in addition to camera and lidar sensors for perception applications. However, the sparsity of…

计算机视觉与模式识别 · 计算机科学 2024-11-12 Felix Fent , Philipp Bauerschmidt , Markus Lienkamp

We survey the mathematical foundations of geometric deep learning, focusing on group equivariant and gauge equivariant neural networks. We develop gauge equivariant convolutional neural networks on arbitrary manifolds $\mathcal{M}$ using…

Graph neural networks (GNNs) have achieved remarkable success in a variety of machine learning tasks over graph data. Existing GNNs usually rely on message passing, i.e., computing node representations by gathering information from the…

机器学习 · 计算机科学 2024-10-15 Junru Zhou , Cai Zhou , Xiyuan Wang , Pan Li , Muhan Zhang

The regression of multiple inter-connected sequence data is a problem in various disciplines. Formally, we name the regression problem of multiple inter-connected data entities as the "dynamic network regression" in this paper. Within the…

机器学习 · 计算机科学 2020-10-19 Yixin Chen , Lin Meng , Jiawei Zhang

Graph neural networks (GNNs) rely mainly on the message-passing paradigm to propagate node features and build interactions, and different graph learning problems require different ranges of node interactions. In this work, we explore the…

机器学习 · 计算机科学 2026-01-08 Fang Wu , Siyuan Li , Stan Z. Li

Graph neural networks (GNNs) are commonly described as being permutation equivariant with respect to node relabeling in the graph. This symmetry of GNNs is often compared to the translation equivariance of Euclidean convolution neural…

机器学习 · 统计学 2023-11-20 Ningyuan Huang , Ron Levie , Soledad Villar

We present a Graph Neural Network (GNN) that accurately simulates a multidisperse suspension of interacting spherical particles. Our machine learning framework is built upon the recent work of Sanchez-Gonzalez et al. ICML, PMLR, 119,…

计算物理 · 物理学 2025-02-20 Aref Hashemi , Aliakbar Izadkhah

In recent years, deep learning techniques have shown great success in various tasks related to inverse problems, where a target quantity of interest can only be observed through indirect measurements by a forward operator. Common approaches…

数值分析 · 数学 2024-03-18 Matthias Beckmann , Nick Heilenkötter

Machine learning frameworks such as graph neural networks typically rely on a given, fixed graph to exploit relational inductive biases and thus effectively learn from network data. However, when said graphs are (partially) unobserved,…

机器学习 · 计算机科学 2022-05-20 Max Wasserman , Saurabh Sihag , Gonzalo Mateos , Alejandro Ribeiro

In many machine learning tasks it is desirable that a model's prediction transforms in an equivariant way under transformations of its input. Convolutional neural networks (CNNs) implement translational equivariance by construction; for…

机器学习 · 计算机科学 2018-03-20 Maurice Weiler , Fred A. Hamprecht , Martin Storath

In recent years, Graph Neural Networks (GNNs) have been utilized for various applications ranging from drug discovery to network design and social networks. In many applications, it is impossible to observe some properties of the graph…

机器学习 · 计算机科学 2025-03-12 Moshe Eliasof , Md Shahriar Rahim Siddiqui , Carola-Bibiane Schönlieb , Eldad Haber

Here we present a machine learning framework and model implementation that can learn to simulate a wide variety of challenging physical domains, involving fluids, rigid solids, and deformable materials interacting with one another. Our…

机器学习 · 计算机科学 2020-09-15 Alvaro Sanchez-Gonzalez , Jonathan Godwin , Tobias Pfaff , Rex Ying , Jure Leskovec , Peter W. Battaglia

This paper introduces Graph Convolutional Recurrent Network (GCRN), a deep learning model able to predict structured sequences of data. Precisely, GCRN is a generalization of classical recurrent neural networks (RNN) to data structured by…

机器学习 · 统计学 2016-12-23 Youngjoo Seo , Michaël Defferrard , Pierre Vandergheynst , Xavier Bresson

Graph neural networks (GNNs), which are capable of learning representations from graphical data, are naturally suitable for modeling molecular systems. This review introduces GNNs and their various applications for small organic molecules.…

机器学习 · 计算机科学 2023-10-10 Yuyang Wang , Zijie Li , Amir Barati Farimani

Graph Neural Networks (GNNs) have paved the way for being a cornerstone in graph-related learning tasks. Yet, the ability of GNNs to capture structural interactions within graphs remains under-explored. In this work, we address this gap by…

机器学习 · 计算机科学 2025-03-04 Asela Hevapathige , Qing Wang

Graph Neural Networks (GNNs) have gained popularity in various learning tasks, with successful applications in fields like molecular biology, transportation systems, and electrical grids. These fields naturally use graph data, benefiting…

机器学习 · 计算机科学 2024-09-23 Caio F. Deberaldini Netto , Zhiyang Wang , Luana Ruiz

Graph Neural Networks (GNNs) have become the leading paradigm for learning on (static) graph-structured data. However, many real-world systems are dynamic in nature, since the graph and node/edge attributes change over time. In recent…

This work proposes a novel methodology for turbulence modeling in Large Eddy Simulation (LES) based on Graph Neural Networks (GNNs), which embeds the discrete rotational, reflectional and translational symmetries of the Navier-Stokes…

流体动力学 · 物理学 2025-04-11 Marius Kurz , Andrea Beck , Benjamin Sanderse