paper-with-me

홈 › Papers

Incidence Networks for Geometric Deep Learning

2019-05-27 · ICML 2020 1 · Marjan Albooyeh, Daniele Bertolini, Siamak Ravanbakhsh

Sparse incidence tensors can represent a variety of structured data. For example, we may represent attributed graphs using their node-node, node-edge, or edge-edge incidence matrices. In higher dimensions, incidence tensors can represent simplicial complexes and polytopes. In this paper, we formalize incidence tensors, analyze their structure, and present the family of equivariant networks that operate on them. We show that any incidence tensor decomposes into invariant subsets. This decomposition, in turn, leads to a decomposition of the corresponding equivariant linear maps, for which we prove an efficient pooling-and-broadcasting implementation.

📄 PDF Abstract BibTeX arXiv:1905.11460

Code (0)

등록된 구현이 없습니다.

Tasks

Deep LearningDrug DiscoveryMolecular Property PredictionRepresentation Learning

Similar Papers 제목 키워드 기반

Do Large Language Models Truly Understand Geometric Structures?

2025-01-23 · XiaoFeng Wang, Yiming Wang, Wenhong Zhu, Rui Wang

Geometric ability is a significant challenge for large language models (LLMs) due to the need for advanced spatial comprehension and abstract thinking. Existing datasets primarily evaluate LLMs on their final answers, bu…

Geometric and Spectral Alignment for Deep Neural Network II

2026-05-04 · Ziran Liu, Wei Wang, Jinhao Wang, Pengcheng Wang 외 arxiv

This paper develops the angular and static-channel component of Geometric and Spectral Alignment for residual Jacobian chains. Starting from Cartan-coordinate rigidity and fitted effective-rank windows, we study how domi…

An Incidence Geometry approach to Dictionary Learning

2014-02-28 · Meera Sitharam, Mohamad Tarifi, Menghan Wang

We study the Dictionary Learning (aka Sparse Coding) problem of obtaining a sparse representation of data points, by learning \emph{dictionary vectors} upon which the data points can be written as sparse linear combinati…

Dictionary Learning

Unifying incidence and prevalence under a time-varying general branching process

2021-07-12 · Mikko S. Pakkanen, Xenia Miscouridou, Matthew J. Penn, Charles Whittaker 외

Renewal equations are a popular approach used in modelling the number of new infections, i.e., incidence, in an outbreak. We develop a stochastic model of an outbreak based on a time-varying variant of the Crump-Mode-Jag…

EpidemiologyProbabilistic Programming

Common Complexes of Decompositions and Complex Balanced Equilibria of Chemical Reaction Networks

2021-09-13 · Lauro L. Fontanil, Eduardo R. Mendoza

A decomposition of a chemical reaction network (CRN) is produced by partitioning its set of reactions. The partition induces networks, called subnetworks, that are "smaller" than the given CRN which, at this point, can b…