English
Related papers

Related papers: A topological model for partial equivariance in de…

200 papers

Transfer learning for partial differential equations (PDEs) is to develop a pre-trained neural network that can be used to solve a wide class of PDEs. Existing transfer learning approaches require much information of the target PDEs such as…

Numerical Analysis · Mathematics 2023-01-30 Zezhong Zhang , Feng Bao , Lili Ju , Guannan Zhang

Inferring topological and geometrical information from data can offer an alternative perspective on machine learning problems. Methods from topological data analysis, e.g., persistent homology, enable us to obtain such information,…

Computer Vision and Pattern Recognition · Computer Science 2018-02-19 Christoph Hofer , Roland Kwitt , Marc Niethammer , Andreas Uhl

This work proposes an autoencoder neural network as a non-linear generalization of projection-based methods for solving Partial Differential Equations (PDEs). The proposed deep learning architecture presented is capable of generating the…

Computational Physics · Physics 2020-06-25 Jaime Lopez Garcia , Angel Rivero Jimenez

Conformal Autoencoders are a neural network architecture that imposes orthogonality conditions between the gradients of latent variables to obtain disentangled representations of data. In this work we show that orthogonality relations…

Machine Learning · Computer Science 2025-07-14 George A. Kevrekidis , Zan Ahmad , Mauro Maggioni , Soledad Villar , Yannis G. Kevrekidis

Spherical equivariant graph neural networks (EGNNs) provide a principled framework for learning on three-dimensional molecular and biomolecular systems, where predictions must respect the rotational symmetries inherent in physics. These…

Machine Learning · Computer Science 2025-12-17 Sophia Tang

Variational Autoencoders (VAEs) are well-established as a principled approach to probabilistic unsupervised learning with neural networks. Typically, an encoder network defines the parameters of a Gaussian distributed latent space from…

Machine Learning · Computer Science 2025-05-16 Alan Jeffares , Liyuan Liu

Topological data analysis (TDA) offers novel mathematical tools for deep learning. Inspired by Carlsson et al., this study designs topology-aware convolutional kernels that significantly improve speech recognition networks. Theoretically,…

Machine Learning · Computer Science 2025-05-28 Zhiwang Yu

Variational Autoencoders (VAEs) have become a popular approach for dimensionality reduction. However, despite their ability to identify latent low-dimensional structures embedded within high-dimensional data, these latent representations…

Machine Learning · Statistics 2020-08-27 Kaspar Märtens , Christopher Yau

How can prior knowledge on the transformation invariances of a domain be incorporated into the architecture of a neural network? We propose Equivariant Transformers (ETs), a family of differentiable image-to-image mappings that improve the…

Computer Vision and Pattern Recognition · Computer Science 2019-05-28 Kai Sheng Tai , Peter Bailis , Gregory Valiant

Understanding how neural representations respond to geometric transformations is essential for evaluating whether learned features preserve meaningful spatial structure. Existing approaches primarily assess robustness primarily by comparing…

Machine Learning · Computer Science 2026-05-12 Huahua Lin , Katayoun Farrahi , Xiaohao Cai

Message passing on hypergraphs has been a standard framework for learning higher-order correlations between hypernodes. Recently-proposed hypergraph neural networks (HGNNs) can be categorized into spatial and spectral methods based on their…

Machine Learning · Computer Science 2024-05-28 Siddhant Saxena , Shounak Ghatak , Raghu Kolla , Debashis Mukherjee , Tanmoy Chakraborty

The classical development of neural networks has been primarily for mappings between a finite-dimensional Euclidean space and a set of classes, or between two finite-dimensional Euclidean spaces. The purpose of this work is to generalize…

This paper explores the efficacy of diffusion-based generative models as neural operators for partial differential equations (PDEs). Neural operators are neural networks that learn a mapping from the parameter space to the solution space of…

Machine Learning · Computer Science 2024-12-17 Katsiaryna Haitsiukevich , Onur Poyraz , Pekka Marttinen , Alexander Ilin

The standard cosmological model with cold dark matter posits a hierarchical formation of structures. We introduce topological neural networks (TNNs), implemented as message-passing neural networks on higher-order structures, to effectively…

Cosmology and Nongalactic Astrophysics · Physics 2025-08-06 Jun-Young Lee , Francisco Villaescusa-Navarro

Labeled sequence transduction is a task of transforming one sequence into another sequence that satisfies desiderata specified by a set of labels. In this paper we propose multi-space variational encoder-decoders, a new model for labeled…

Computation and Language · Computer Science 2019-10-08 Chunting Zhou , Graham Neubig

The deep operator networks (DeepONet), a class of neural operators that learn mappings between function spaces, have recently been developed as surrogate models for parametric partial differential equations (PDEs). In this work we propose a…

Machine Learning · Computer Science 2024-10-31 Yuan Qiu , Nolan Bridges , Peng Chen

Neural operators (NOs) are a class of deep learning models designed to simultaneously solve infinitely many related problems by casting them into an infinite-dimensional space, whereon these NOs operate. A significant gap remains between…

Machine Learning · Computer Science 2025-08-22 Anastasis Kratsios , Ariel Neufeld , Philipp Schmocker

Learning the mapping between two function spaces has garnered considerable research attention. However, learning the solution operator of partial differential equations (PDEs) remains a challenge in scientific computing. Fourier neural…

Machine Learning · Computer Science 2024-03-05 Jin Young Shin , Jae Yong Lee , Hyung Ju Hwang

Variational autoencoders (VAEs) learn representations of data by jointly training a probabilistic encoder and decoder network. Typically these models encode all features of the data into a single variable. Here we are interested in learning…

Incorporating symmetries can lead to highly data-efficient and generalizable models by defining equivalence classes of data samples related by transformations. However, characterizing how transformations act on input data is often…

Machine Learning · Computer Science 2022-07-04 Jung Yeon Park , Ondrej Biza , Linfeng Zhao , Jan Willem van de Meent , Robin Walters