EdgeNets: Edge Varying Graph Neural Networks

Driven by the outstanding performance of neural networks in the structured euclidean domain, recent years have seen a surge of interest in developing neural networks for graphs and data supported on graphs. The graph is leveraged at each layer of the neural network as a parameterization to capture detail at the node level with a reduced...

Graph filter designs and implementations

The ability to model irregular data and the interactions between them have<br/>extended the traditional signal processing tools to the graph domain. Under<br/>these circumstances, the emergence of graph signal processing has offered a<br/>brand new framework for dealing with complex data. In particular, the graph<br/>Fourier transform (GFT) lets...

Graph-time signal processing: Filtering and sampling strategies

The necessity to process signals living in non-Euclidean domains, such as signals defined on the top of a graph, has led to the extension of signal processing techniques to the graph setting. Among different approaches, graph signal processing distinguishes itself by providing a Fourier analysis of these signals. Analogously to the Fourier...

Convolutional Neural Network Architectures for Signals Supported on Graphs

Two architectures that generalize convolutional neural networks (CNNs) for the processing of signals supported on graphs are introduced. We start with the selection graph neural network (GNN), which replaces linear time invariant filters with linear shift invariant graph filters to generate convolutional features and reinterprets pooling as a...

Advances in Distributed Graph Filtering

Graph filters are one of the core tools in graph signal processing. A central aspect of them is their direct distributed implementation. However, the filtering performance is often traded with distributed communication and computational savings. To improve this tradeoff, this paper generalizes state-of-the-art distributed graph filters to...

On the Limits of Finite-Time Distributed Consensus Through Successive Local Linear Operations

In this work, we explore the limits of finite-time distributed consensus through the intersection of graph filters and matrix function theory. We focus on algorithms capable to compute the consensus exactly through filtering operations over a graph, and that have been proven to converge in finite time. In this context, we show that there...

Asynchronous Distributed Edge-Variant Graph Filters

As the size of the sensor network grows, synchronization starts to become the main bottleneck for distributed computing. As a result, efforts in several areas have been focused on the convergence analysis of asynchronous computational methods. In this work, we aim to cross-pollinate distributed graph filters with results in parallel computing...

Distributed edge-variant graph filters

The main challenges distributed graph filters face in practice are the communication overhead and computational complexity. In this work, we extend the state-of-the-art distributed finite impulse response (FIR) graph filters to an edge-variant (EV) version, i.e., a filter where every node weights the signals from its neighbors with different...

Filtering Random Graph Processes over Random Time-Varying Graphs

Graph filters play a key role in processing the graph spectra of signals supported on the vertices of a graph. However, despite their widespread use, graph filters have been analyzed only in the deterministic setting, ignoring the impact of stochasticity in both the graph topology and the signal itself. To bridge this gap, we examine the...

Distributed Graph Filters

We have recently seen a surge of research focusing on the processing of graph data. The emerging field of signal processing on graphs focuses on the extension of classical discrete signal processing techniques to the graph setting. Arguably, the greatest breakthrough of the field has been the extension of the Fourier transform from time signals...