English
Related papers

Related papers: Diffusion Scattering Transforms on Graphs

200 papers

Convolutional neural networks (CNNs) constructed natively on the sphere have been developed recently and shown to be highly effective for the analysis of spherical data. While an efficient framework has been formulated, spherical CNNs are…

Computer Vision and Pattern Recognition · Computer Science 2022-01-25 Jason D. McEwen , Christopher G. R. Wallis , Augustine N. Mavor-Parker

Neural Style Transfer (NST) is the field of study applying neural techniques to modify the artistic appearance of a content image to match the style of a reference style image. Traditionally, NST methods have focused on texture-based image…

Computer Vision and Pattern Recognition · Computer Science 2023-07-12 Dan Ruta , Gemma Canet Tarrés , Andrew Gilbert , Eli Shechtman , Nicholas Kolkin , John Collomosse

We present a novel framework for discrete multiresolution analysis of graph signals. The main analytical tool is the samplet transform, originally defined in the Euclidean framework as a discrete wavelet-like construction, tailored to the…

Signal Processing · Electrical Eng. & Systems 2025-07-28 Giacomo Elefante , Gianluca Giacchi , Michael Multerer , Jacopo Quizi

Data with geometric structure is ubiquitous in machine learning often arising from fundamental symmetries in a domain, such as permutation-invariance in graphs and translation-invariance in images. Group-convolutional architectures, which…

Machine Learning · Computer Science 2024-10-10 Bobak T. Kiani , Lukas Fesser , Melanie Weber

We prove a scattering result near certain steady states for a Hartree equation for a random field. This equation describes the evolution of a system of infinitely many particles. It is an analogous formulation of the usual Hartree equation…

Analysis of PDEs · Mathematics 2020-07-02 Charles Collot , Anne-Sophie de Suzzoni

We consider a damped linear hyperbolic system modelling the propagation of pressure waves in a network of pipes. Well-posedness is established via semi-group theory and the existence of a unique steady state is proven in the absence of…

Numerical Analysis · Mathematics 2016-05-11 Herbert Egger , Thomas Kugler

We present a graph theory-based method to characterise flow defects and structural shifts in condensed matter. We explore the connection between dynamical properties, particularly the recently introduced concept of ''softness'', and…

Disordered Systems and Neural Networks · Physics 2024-08-13 An Wang , Gabriele C. Sosso

A novel spherical convolution is defined through the sifting property of the Dirac delta on the sphere. The so-called sifting convolution is defined by the inner product of one function with a translated version of another, but with the…

Information Theory · Computer Science 2023-04-24 Patrick J. Roddy , Jason D. McEwen

We propose a new way of thinking about one parameter persistence. We believe topological persistence is fundamentally not about decomposition theorems but a central role is played by a choice of metrics. Choosing a pseudometric between…

Algebraic Topology · Mathematics 2020-02-07 Wojciech Chachólski , Henri Riihimäki

Diffusion models have become a leading framework in generative modeling, yet their theoretical understanding -- especially for high-dimensional data concentrated on low-dimensional structures -- remains incomplete. This paper investigates…

Machine Learning · Computer Science 2026-04-29 Zixuan Zhang , Kaixuan Huang , Tuo Zhao , Mengdi Wang , Minshuo Chen

We consider a Hartree equation for a random variable, which describes the temporal evolution of infinitely many Fermions. On the Euclidean space, this equation possesses equilibria which are not localised. We show their stability through a…

Analysis of PDEs · Mathematics 2018-11-09 Charles Collot , Anne-Sophie de Suzzoni

We study the defocusing energy-critical nonlinear wave equation in four dimensions. Our main result proves the stability of the scattering mechanism under random pertubations of the initial data. The random pertubation is defined through a…

Analysis of PDEs · Mathematics 2025-06-03 Bjoern Bringmann

We present diffusion-convolutional neural networks (DCNNs), a new model for graph-structured data. Through the introduction of a diffusion-convolution operation, we show how diffusion-based representations can be learned from…

Machine Learning · Computer Science 2016-07-11 James Atwood , Don Towsley

Wireless signals are integral to modern society, enabling both communication and increasingly, environmental sensing. While various propagation models exist, ranging from empirical methods to full-wave simulations, the phenomenon of…

Signal Processing · Electrical Eng. & Systems 2025-09-10 Anurag Pallaprolu , Winston Hurst , Yasamin Mostofi

Deep learning is an increasingly popular approach for inverting surface wave dispersion curves to obtain Vs profiles. However, its generalizability is constrained by the depth and velocity scales of training data. We propose a unified deep…

Geophysics · Physics 2025-09-30 Tianjian Cheng , Hongrui Xu , Jiayu Feng , Xiongyu Hu , Chaofan Yao

In an ultrasonic array system, increasing the aperture size to achieve a high resolution requires more transmit and receive channels, thus making it essential to have an analysis technique that can reconstruct the shape and physical…

Optics · Physics 2025-08-21 Kai Yabumoto , Takayoshi Yumii , Kenjiro Kimura

Graph convolutional neural networks (GCNNs) are nonlinear processing tools to learn representations from network data. A key property of GCNNs is their stability to graph perturbations. Current analysis considers deterministic perturbations…

Machine Learning · Computer Science 2021-06-22 Zhan Gao , Elvin Isufi , Alejandro Ribeiro

Metasurfaces enable powerful control of electromagnetic waves using subwavelength planar structures, but their deeply subwavelength periodicity typically suppresses propagating diffraction orders, which limits the number of available…

Optics · Physics 2026-05-14 Karim Achouri

Reaction diffusion systems are often used to study pattern formation in biological systems. However, most methods for understanding their behavior are challenging and can rarely be applied to complex systems common in biological…

Analysis of PDEs · Mathematics 2013-05-24 William R. Holmes

Planar wave trains are traveling wave solutions whose wave profiles are periodic in one spatial direction and constant in the transverse direction. In this paper, we investigate the stability of planar wave trains in reaction-diffusion…

Analysis of PDEs · Mathematics 2021-01-14 Björn de Rijk , Björn Sandstede