Attention layers, as commonly used in transformers, form the backbone of modern deep
learning, yet there is no mathematical description of their benefits and deficiencies as …

A local algorithm is a distributed algorithm that runs in constant time, independently of the
size of the network. Being highly scalable and fault tolerant, such algorithms are ideal in the …

Abstract Graph Neural Networks (GNNs) have been shown to be effective models for
different predictive tasks on graph-structured data. Recent work on their expressive power …

While Graph Neural Networks (GNNs) have achieved remarkable results in a variety of
applications, recent studies exposed important shortcomings in their ability to capture the …

Elements of the theory of dynamic networks Page 1 72 COMMUNICATIONS OF THE ACM |
FEBRUARY 2018 | VOL. 61 | NO. 2 review articles IMA GE B Y ANITHA DEVI MUR THI A …

This paper studies the expressive power of graph neural networks falling within the
message-passing framework (GNNmp). Two results are presented. First, GNNmp are shown …

Graph neural networks (GNNs) are powerful machine learning models for various graph
learning tasks. Recently, the limitations of the expressive power of various GNN models …

Deep learning-based approaches have been developed to solve challenging problems in
wireless communications, leading to promising results. Early attempts adopted neural …

Parameterized complexity/multivariate complexity algorithmics is an exciting field of modern
algorithm design and analysis, with a broad range of theoretical and practical aspects that …

Abstract Graph Neural Networks (GNNs), neural network architectures targeted to learning
representations of graphs, have become a popular learning model for prediction tasks on …