English
Related papers

Related papers: Nonlinear Sheaf Diffusion in Graph Neural Networks

200 papers

A Sheaf Neural Network (SNN) is a type of Graph Neural Network (GNN) that operates on a sheaf, an object that equips a graph with vector spaces over its nodes and edges and linear maps between these spaces. SNNs have been shown to have…

Physical systems with complex unsteady dynamics, such as fluid flows, are often poorly represented by a single mean solution. For many practical applications, it is crucial to access the full distribution of possible states, from which…

Computational Physics · Physics 2025-04-07 Mario Lino , Tobias Pfaff , Nils Thuerey

The focus of this thesis is the construction and analysis of efficient representations in nonlinear signal processing, and the applications of these structures to inverse problems in a variety of fields. The work is composed of three major…

Classical Analysis and ODEs · Mathematics 2021-09-21 Eugene Brevdo

Models of network diffusion typically rely on the Laplacian matrix, capturing interactions via direct connections. Beyond direct interactions, information in many systems can also flow via indirect pathways, where influence typically…

Physics and Society · Physics 2025-10-10 Lluís Torres-Hugas , Jordi Duch , Sergio Gómez

Convolutional Neural Networks are extremely efficient architectures in image and audio recognition tasks, thanks to their ability to exploit the local translational invariance of signal classes over their domain. In this paper we consider…

Machine Learning · Computer Science 2014-05-22 Joan Bruna , Wojciech Zaremba , Arthur Szlam , Yann LeCun

Diffusing a graph signal at multiple scales requires computing the action of the exponential of several multiples of the Laplacian matrix. We tighten a bound on the approximation error of truncated Chebyshev polynomial approximations of the…

Signal Processing · Electrical Eng. & Systems 2021-05-03 Sibylle Marcotte , Amélie Barbe , Rémi Gribonval , Titouan Vayer , Marc Sebban , Pierre Borgnat , Paulo Gonçalves

Graph convolutional neural networks (GCNNs) have been widely used in graph learning. It has been observed that the smoothness functional on graphs can be defined in terms of the graph Laplacian. This fact points out in the direction of…

Machine Learning · Computer Science 2020-09-30 Asif Salim , Sumitra S

The primary objective of this thesis is to develop novel algorithmic approaches for Graph Representation Learning of static and single-event dynamic networks. In such a direction, we focus on the family of Latent Space Models, and more…

Machine Learning · Computer Science 2025-12-22 Nikolaos Nakis

We develop a novel framework for modeling diffusion on complex networks by constructing Laplacian-like operators based on walks around a graph. Our approach introduces a parametric family of walk-based Laplacians that naturally incorporate…

Social and Information Networks · Computer Science 2026-01-19 Francesca Arrigo , Fabio Durastante

The dominating NLP paradigm of training a strong neural predictor to perform one task on a specific dataset has led to state-of-the-art performance in a variety of applications (eg. sentiment classification, span-prediction based question…

Computation and Language · Computer Science 2021-09-06 Paul Michel

This paper analyses LightGCN in the context of graph recommendation algorithms. Despite the initial design of Graph Convolutional Networks for graph classification, the non-linear operations are not always essential. LightGCN enables linear…

Information Retrieval · Computer Science 2023-12-29 Milena Kapralova , Luca Pantea , Andrei Blahovici

In this paper, we introduce a novel concept for learning of the parameters in a neural network. Our idea is grounded on modeling a learning problem that addresses a trade-off between (i) satisfying local objectives at each node and (ii)…

Machine Learning · Computer Science 2019-02-04 Dimche Kostadinov , Behrooz Razdehi , Slava Voloshynovskiy

Dynamical processes on networks are currently being considered in different domains of cross-disciplinary interest. Reaction-diffusion systems hosted on directed graphs are in particular relevant for their widespread applications, from…

Statistical Mechanics · Physics 2016-04-06 Silvia Contemori , Francesca Di Patti , Duccio Fanelli , Filippo Miele

Graph Neural Networks (GNNs) have received increasing attention for representation learning in various machine learning tasks. However, most existing GNNs applying neighborhood aggregation usually perform poorly on the graph with…

Machine Learning · Computer Science 2024-10-29 Wei Zhuo , Guang Tan

In this work, a novel approach for the construction and training of time series models is presented that deals with the problem of learning on large time series with non-equispaced observations, which at the same time may possess features…

Machine Learning · Computer Science 2020-11-25 Charilaos Mylonas , Eleni Chatzi

Diffuse interface methods have recently been introduced for the task of semi-supervised learning. The underlying model is well-known in materials science but was extended to graphs using a Ginzburg--Landau functional and the graph…

Machine Learning · Statistics 2016-11-21 Jessica Bosch , Steffen Klamt , Martin Stoll

Laplacian mixture models identify overlapping regions of influence in unlabeled graph and network data in a scalable and computationally efficient way, yielding useful low-dimensional representations. By combining Laplacian eigenspace and…

Machine Learning · Statistics 2018-10-03 Daniel Korenblum

Graph Neural Networks (GNNs) traditionally employ a message-passing mechanism that resembles diffusion over undirected graphs, which often leads to homogenization of node features and reduced discriminative power in tasks such as node…

Machine Learning · Computer Science 2025-03-04 Seong Ho Pahng , Sahand Hormoz

Combinatorial and topological structures, such as graphs, simplicial complexes, and cell complexes, form the foundation of geometric and topological deep learning (GDL and TDL) architectures. These models aggregate signals over such…

Machine Learning · Computer Science 2026-05-28 Chuan-Shen Hu

Graphs are a highly expressive abstraction for modeling entities and their relations, such as molecular structures, social networks, and traffic networks. Deep Graph Networks (DGNs) have emerged as a family of deep learning models that can…

Machine Learning · Computer Science 2024-10-16 Alessio Gravina