no code implementations • 16 Dec 2023 • Andrei Buciulea, Elvin Isufi, Geert Leus, Antonio G. Marques
Graphs are widely used to represent complex information and signal domains with irregular support.
no code implementations • 4 Dec 2023 • Zhan Gao, Amanda Prorok, Elvin Isufi
Analyzing the stability of graph neural networks (GNNs) under topological perturbations is key to understanding their transferability and the role of each architecture component.
no code implementations • 30 Nov 2023 • Alexander Möllers, Alexander Immer, Elvin Isufi, Vincent Fortuin
Graph contrastive learning has shown great promise when labeled data is scarce, but large unlabeled datasets are available.
1 code implementation • 30 Oct 2023 • Maosheng Yang, Viacheslav Borovitskiy, Elvin Isufi
We propose principled Gaussian processes (GPs) for modeling functions defined over the edge set of a simplicial 2-complex, a structure similar to a graph in which edges may form triangular faces.
no code implementations • 14 Sep 2023 • Alexander Möllers, Alexander Immer, Vincent Fortuin, Elvin Isufi
We leverage this decomposition to develop a contrastive self-supervised learning approach for processing simplicial data and generating embeddings that encapsulate specific spectral information. Specifically, we encode the pertinent data invariances through simplicial neural networks and devise augmentations that yield positive contrastive examples with suitable spectral properties for downstream tasks.
no code implementations • 26 Jan 2023 • Maosheng Yang, Elvin Isufi
We propose a simplicial complex convolutional neural network (SCCNN) to learn data representations on simplicial complexes.
no code implementations • 17 Jan 2023 • Bishwadeep Das, Elvin Isufi
We propose an online update of the filter, based on the principles of online machine learning.
1 code implementation • 4 Jan 2023 • Benjamin Habib, Elvin Isufi, Ward van Breda, Arjen Jongepier, Jochen L. Cremer
While data-driven alternatives based on Machine Learning models could be a choice, they suffer in DSSE because of the lack of labeled data.
no code implementations • 16 Nov 2022 • Elvin Isufi, Fernando Gama, David I. Shuman, Santiago Segarra
For time series and image data that reside on Euclidean domains, filters are the crux of many signal processing and machine learning techniques, including convolutional neural networks.
no code implementations • 13 Nov 2022 • Zhan Gao, Elvin Isufi
Stability of graph neural networks (GNNs) characterizes how GNNs react to graph perturbations and provides guarantees for architecture performance in noisy scenarios.
no code implementations • 30 Jun 2022 • Mohammad Sabbaqi, Elvin Isufi
The proposed approach can work with any type of product graph and we also introduce a parametric product graph to learn also the spatiotemporal coupling.
no code implementations • 15 Mar 2022 • Bishwadeep Das, Elvin Isufi
Specifically, we propose a stochastic attachment model for incoming nodes parameterized by the attachment probabilities and edge weights.
no code implementations • 15 Mar 2022 • Bishwadeep Das, Elvin Isufi
We propose a filter learning scheme for data over expanding graphs by relying only on such a model.
no code implementations • 29 Jan 2022 • Zhan Gao, Elvin Isufi
To overcome this issue, we propose a variance-constrained optimization problem for SGNNs, balancing the expected performance and the stochastic deviation.
no code implementations • 29 Jan 2022 • Elvin Isufi, Maosheng Yang
This paper proposes convolutional filtering for data whose structure can be modeled by a simplicial complex (SC).
no code implementations • 27 Jan 2022 • Maosheng Yang, Elvin Isufi, Michael T. Schaub, Geert Leus
We study linear filters for processing signals supported on abstract topological spaces modeled as simplicial complexes, which may be interpreted as generalizations of graphs that account for nodes, edges, triangular faces etc.
no code implementations • 21 Oct 2021 • Alberto Natali, Elvin Isufi, Mario Coutino, Geert Leus
This work proposes an algorithmic framework to learn time-varying graphs from online data.
no code implementations • 6 Oct 2021 • Maosheng Yang, Elvin Isufi, Geert Leus
Graphs can model networked data by representing them as nodes and their pairwise relationships as edges.
no code implementations • 19 Jun 2021 • Zhan Gao, Elvin Isufi, Alejandro Ribeiro
In particular, it proves the expected output difference between the GCNN over random perturbed graphs and the GCNN over the nominal graph is upper bounded by a factor that is linear in the link loss probability.
no code implementations • 23 Mar 2021 • Maosheng Yang, Elvin Isufi, Michael T. Schaub, Geert Leus
In this paper, we study linear filters to process signals defined on simplicial complexes, i. e., signals defined on nodes, edges, triangles, etc.
no code implementations • 2 Mar 2021 • Elvin Isufi, Gabriele Mazzola
We develop a graph-time convolutional filter by following the shift-and-sum principles of the convolutional operator to learn higher-level features over the product graph.
no code implementations • 27 Oct 2020 • Luana Ruiz, Fernando Gama, Alejandro Ribeiro, Elvin Isufi
In this work, we approach GCNNs from a state-space perspective revealing that the graph convolutional module is a minimalistic linear state-space model, in which the state update matrix is the graph shift operator.
no code implementations • 22 Oct 2020 • Alberto Natali, Mario Coutino, Elvin Isufi, Geert Leus
Signal processing and machine learning algorithms for data supported over graphs, require the knowledge of the graph topology.
1 code implementation • 14 Sep 2020 • Bianca Iancu, Luana Ruiz, Alejandro Ribeiro, Elvin Isufi
Activation functions are crucial in graph neural networks (GNNs) as they allow defining a nonlinear family of functions to capture the relationship between the input graph data and their representations.
no code implementations • 4 Jun 2020 • Zhan Gao, Elvin Isufi, Alejandro Ribeiro
Graph neural networks (GNNs) model nonlinear representations in graph data with applications in distributed agent coordination, control, and planning among others.
no code implementations • 17 Apr 2020 • Alberto Natali, Elvin Isufi, Geert Leus
The forecasting of multi-variate time processes through graph-based techniques has recently been addressed under the graph signal processing framework.
1 code implementation • 8 Mar 2020 • Fernando Gama, Elvin Isufi, Geert Leus, Alejandro Ribeiro
We also introduce GNN extensions using edge-varying and autoregressive moving average graph filters and discuss their properties.
1 code implementation • 21 Jan 2020 • Elvin Isufi, Fernando Gama, Alejandro Ribeiro
This is a general linear and local operation that a node can perform and encompasses under one formulation all existing graph convolutional neural networks (GCNNs) as well as graph attention networks (GATs).
no code implementations • 4 Mar 2019 • Elvin Isufi, Fernando Gama, Alejandro Ribeiro
This paper reviews graph convolutional neural networks (GCNNs) through the lens of edge-variant graph filters.
no code implementations • 29 Jan 2019 • Ron Levie, Elvin Isufi, Gitta Kutyniok
For filters in this space, the perturbation in the filter is bounded by a constant times the perturbation in the graph, and filters in the Cayley smoothness space are thus termed linearly stable.
no code implementations • 12 Sep 2017 • Paolo Di Lorenzo, Paolo Banelli, Elvin Isufi, Sergio Barbarossa, Geert Leus
Numerical simulations carried out over both synthetic and real data illustrate the good performance of the proposed sampling and reconstruction strategies for (possibly distributed) adaptive learning of signals defined over graphs.
no code implementations • 14 Feb 2016 • Elvin Isufi, Andreas Loukas, Andrea Simonetto, Geert Leus
We design a family of autoregressive moving average (ARMA) recursions, which (i) are able to approximate any desired graph frequency response, and (ii) give exact solutions for tasks such as graph signal denoising and interpolation.