no code implementations • 20 Dec 2023 • Lucia Testa, Claudio Battiloro, Stefania Sardellitti, Sergio Barbarossa
In this work, we study the problem of stability of Graph Convolutional Neural Networks (GCNs) under random small perturbations in the underlying graph topology, i. e. under a limited number of insertions or deletions of edges.
1 code implementation • 27 Nov 2023 • Gabriele D'Acunto, Paolo Di Lorenzo, Francesco Bonchi, Stefania Sardellitti, Sergio Barbarossa
Despite the large research effort devoted to learning dependencies between time series, the state of the art still faces a major limitation: existing methods learn partial correlations but fail to discriminate across distinct frequency bands.
1 code implementation • 5 Sep 2023 • Claudio Battiloro, Lucia Testa, Lorenzo Giusti, Stefania Sardellitti, Paolo Di Lorenzo, Sergio Barbarossa
The aim of this work is to introduce Generalized Simplicial Attention Neural Networks (GSANs), i. e., novel neural architectures designed to process data defined on simplicial complexes using masked self-attentional layers.
no code implementations • 16 Feb 2023 • Claudio Battiloro, Stefania Sardellitti, Sergio Barbarossa, Paolo Di Lorenzo
Weighing the topological domain over which data can be represented and analysed is a key strategy in many signal processing and machine learning applications, enabling the extraction and exploitation of meaningful data features and their (higher order) relationships.
1 code implementation • 16 Sep 2022 • Lorenzo Giusti, Claudio Battiloro, Lucia Testa, Paolo Di Lorenzo, Stefania Sardellitti, Sergio Barbarossa
In this paper, we introduce Cell Attention Networks (CANs), a neural architecture operating on data defined over the vertices of a graph, representing the graph as the 1-skeleton of a cell complex introduced to capture higher order interactions.
Ranked #7 on Graph Classification on NCI109
no code implementations • 22 Jan 2022 • Stefania Sardellitti, Sergio Barbarossa
To overcome this limit, in this paper we extend TSP to deal with signals defined over cell complexes and we also generalize the concept of cell complexes to include hollow cells.
no code implementations • 13 Dec 2021 • Stefania Sardellitti, Sergio Barbarossa, Lucia Testa
The Topological Signal Processing (TSP) framework has been recently developed to analyze signals defined over simplicial complexes, i. e. topological spaces represented by finite sets of elements that are closed under inclusion of subsets [1].
1 code implementation • 26 Jul 2019 • Sergio Barbarossa, Stefania Sardellitti
The goal of this paper is to establish the fundamental tools to analyze signals defined over a topological space, i. e. a set of points along with a set of neighborhood relations.
no code implementations • 18 Feb 2016 • Paolo Di Lorenzo, Sergio Barbarossa, Paolo Banelli, Stefania Sardellitti
The aim of this paper is to propose a least mean squares (LMS) strategy for adaptive estimation of signals defined over graphs.