Generalized Simplicial Attention Neural Networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Battiloro, Claudio, Testa, Lucia, Giusti, Lorenzo, Sardellitti, Stefania, Di Lorenzo, Paolo, Barbarossa, Sergio
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929542002638848
author Battiloro, Claudio
Testa, Lucia
Giusti, Lorenzo
Sardellitti, Stefania
Di Lorenzo, Paolo
Barbarossa, Sergio
author_facet Battiloro, Claudio
Testa, Lucia
Giusti, Lorenzo
Sardellitti, Stefania
Di Lorenzo, Paolo
Barbarossa, Sergio
contents Graph machine learning methods excel at leveraging pairwise relations present in the data. However, graphs are unable to fully capture the multi-way interactions inherent in many complex systems. An effective way to incorporate them is to model the data on higher-order combinatorial topological spaces, such as Simplicial Complexes (SCs) or Cell Complexes. For this reason, we introduce Generalized Simplicial Attention Neural Networks (GSANs), novel neural network architectures designed to process data living on simplicial complexes using masked self-attentional layers. Hinging on topological signal processing principles, we devise a series of principled self-attention mechanisms able to process data associated with simplices of various order, such as nodes, edges, triangles, and beyond. These schemes learn how to combine data associated with neighbor simplices of consecutive order in a task-oriented fashion, leveraging on the simplicial Dirac operator and its Dirac decomposition. We also prove that GSAN satisfies two fundamental properties: permutation equivariance and simplicial-awareness. Finally, we illustrate how our approach compares favorably with other simplicial and graph models when applied to several (inductive and transductive) tasks such as trajectory prediction, missing data imputation, graph classification, and simplex prediction.
format Preprint
id arxiv_https___arxiv_org_abs_2309_02138
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Generalized Simplicial Attention Neural Networks
Battiloro, Claudio
Testa, Lucia
Giusti, Lorenzo
Sardellitti, Stefania
Di Lorenzo, Paolo
Barbarossa, Sergio
Machine Learning
Artificial Intelligence
Algebraic Topology
Graph machine learning methods excel at leveraging pairwise relations present in the data. However, graphs are unable to fully capture the multi-way interactions inherent in many complex systems. An effective way to incorporate them is to model the data on higher-order combinatorial topological spaces, such as Simplicial Complexes (SCs) or Cell Complexes. For this reason, we introduce Generalized Simplicial Attention Neural Networks (GSANs), novel neural network architectures designed to process data living on simplicial complexes using masked self-attentional layers. Hinging on topological signal processing principles, we devise a series of principled self-attention mechanisms able to process data associated with simplices of various order, such as nodes, edges, triangles, and beyond. These schemes learn how to combine data associated with neighbor simplices of consecutive order in a task-oriented fashion, leveraging on the simplicial Dirac operator and its Dirac decomposition. We also prove that GSAN satisfies two fundamental properties: permutation equivariance and simplicial-awareness. Finally, we illustrate how our approach compares favorably with other simplicial and graph models when applied to several (inductive and transductive) tasks such as trajectory prediction, missing data imputation, graph classification, and simplex prediction.
title Generalized Simplicial Attention Neural Networks
topic Machine Learning
Artificial Intelligence
Algebraic Topology
url https://arxiv.org/abs/2309.02138