English
Related papers

Related papers: Heat Kernel Goes Topological

200 papers

This paper presents a mathematically rigorous framework for brain-inspired representation learning founded on the interplay between persistent topological structures and cohomological flows. Neural computation is reformulated as the…

Machine Learning · Computer Science 2025-12-10 Preksha Girish , Rachana Mysore , Mahanthesha U , Shrey Kumar , Shipra Prashant

Persistence diagrams, the most common descriptors of Topological Data Analysis, encode topological properties of data and have already proved pivotal in many different applications of data science. However, since the (metric) space of…

Machine Learning · Statistics 2020-03-10 Mathieu Carrière , Frédéric Chazal , Yuichi Ike , Théo Lacombe , Martin Royer , Yuhei Umeda

Recent work in graph neural networks (GNNs) has led to improvements in molecular activity and property prediction tasks. Unfortunately, GNNs often fail to capture the relative importance of interactions between molecular substructures, in…

Machine Learning · Computer Science 2020-04-03 Emmanuel Noutahi , Dominique Beaini , Julien Horwood , Sébastien Giguère , Prudencio Tossou

This overview article makes the case for how topological concepts can enrich research in machine learning. Using the Euler Characteristic Transform (ECT), a geometrical-topological invariant, as a running example, I present different use…

Machine Learning · Computer Science 2026-01-16 Bastian Rieck

In this paper, we continue the development of the Cartan neural networks programme, launched with three previous publications, by focusing on some mathematical foundational aspects that we deem necessary for our next steps forward. The…

Machine Learning · Computer Science 2025-08-25 Pietro Fré , Federico Milanesio , Marcelo Oyarzo , Matteo Santoro , Mario Trigiante

The aim of this paper is to introduce a novel dictionary learning algorithm for sparse representation of signals defined over combinatorial topological spaces, specifically, regular cell complexes. Leveraging Hodge theory, we embed topology…

Signal Processing · Electrical Eng. & Systems 2025-03-17 Enrico Grimaldi , Claudio Battiloro , Paolo Di Lorenzo

Although deep learning approaches have had tremendous success in image, video and audio processing, computer vision, and speech recognition, their applications to three-dimensional (3D) biomolecular structural data sets have been hindered…

Quantitative Methods · Quantitative Biology 2017-11-01 Zixuan Cang , Guo-Wei Wei

The combinations of machine learning with ab initio methods have attracted much attention for their potential to resolve the accuracy-efficiency dilemma and facilitate calculations for large-scale systems. Recently, equivariant message…

Computational Physics · Physics 2025-09-08 Zhixin Liang , Yunlong Wang , Chi Ding , Junjie Wang , Hui-Tian Wang , Dingyu Xing , Jian Sun

We present a new recurrent neural network topology to enhance state-of-the-art machine learning systems by incorporating a broader context. Our approach overcomes recent limitations with extended narratives through a multi-layered…

Computation and Language · Computer Science 2018-08-07 Patrick Huber , Jan Niehues , Alex Waibel

The heat kernel for the Cauchy-Riemann subLaplacian on S(2n+1) is derived in a manner which is completely analogous to the classical derivation of elliptic heat kernels. This suggests that the classical hamiltonian construction of elliptic…

Analysis of PDEs · Mathematics 2013-03-05 Peter C. Greiner

Deep learning is changing many areas in molecular physics, and it has shown great potential to deliver new solutions to challenging molecular modeling problems. Along with this trend arises the increasing demand of expressive and versatile…

Machine Learning · Computer Science 2023-12-27 Jun Zhang , Yao-Kun Lei , Yaqiang Zhou , Yi Isaac Yang , Yi Qin Gao

Though commonly found in the real world, directed networks have received relatively less attention from the literature in which concerns their topological and dynamical characteristics. In this work, we develop a magnetic Laplacian-based…

Social and Information Networks · Computer Science 2018-12-11 Bruno Messias , Luciano da F. Costa

Topology can extract the structural information in a dataset efficiently. In this paper, we attempt to incorporate topological information into a multiple output Gaussian process model for transfer learning purposes. To achieve this goal,…

Machine Learning · Computer Science 2023-11-01 Hengrui Luo , Jisu Kim , Alice Patania , Mikael Vejdemo-Johansson

In this paper, we introduce a new image representation based on a multilayer kernel machine. Unlike traditional kernel methods where data representation is decoupled from the prediction task, we learn how to shape the kernel with…

Machine Learning · Statistics 2016-10-26 Julien Mairal

It is challenging to guide neural network (NN) learning with prior knowledge. In contrast, many known properties, such as spatial smoothness or seasonality, are straightforward to model by choosing an appropriate kernel in a Gaussian…

Machine Learning · Computer Science 2024-02-29 Ziyang Jiang , Tongshu Zheng , Yiling Liu , David Carlson

The convolutional neural network (CNN) is one of the most commonly used architectures for computer vision tasks. The key building block of a CNN is the convolutional kernel that aggregates information from the pixel neighborhood and shares…

Image and Video Processing · Electrical Eng. & Systems 2022-02-08 Tianyu Ma , Alan Q. Wang , Adrian V. Dalca , Mert R. Sabuncu

Graph Neural Networks (GNNs) effectively learn from relational data by leveraging graph symmetries. However, many real-world systems -- such as biological or social networks -- feature multi-way interactions that GNNs fail to capture.…

Machine Learning · Computer Science 2025-11-21 Mathilde Papillon , Guillermo Bernárdez , Claudio Battiloro , Nina Miolane

We introduce scalable deep kernels, which combine the structural properties of deep learning architectures with the non-parametric flexibility of kernel methods. Specifically, we transform the inputs of a spectral mixture base kernel with a…

Machine Learning · Computer Science 2015-11-09 Andrew Gordon Wilson , Zhiting Hu , Ruslan Salakhutdinov , Eric P. Xing

Earlier in the study of the combinatorial properties of the heat kernel of Laplace operator with covariant derivative diagram technique and matrix formalism were constructed. In particular, this formalism allows you to control the…

Mathematical Physics · Physics 2018-08-27 Aleksandr Ivanov

The convolution operator at the core of many modern neural architectures can effectively be seen as performing a dot product between an input matrix and a filter. While this is readily applicable to data such as images, which can be…

Machine Learning · Computer Science 2025-11-26 Luca Cosmo , Giorgia Minello , Alessandro Bicciato , Michael Bronstein , Emanuele Rodolà , Luca Rossi , Andrea Torsello