79 citations · 205 across the 9 of their papers we have counts for
12 papers
CIN++: Enhancing Topological Message Passing
Lorenzo Giusti, Teodora Reu, Francesco Ceccarelli +2
Graph Neural Networks (GNNs) have demonstrated remarkable success in learning from graph-structured data. However, they face significant limitations in expressive power, struggling…
On Over-Squashing in Message Passing Neural Networks: The Impact of Width, Depth, and Topology
Francesco Di Giovanni, Lorenzo Giusti, Federico Barbero +3
Message Passing Neural Networks (MPNNs) are instances of Graph Neural Networks that leverage the graph to send messages over the edges. This inductive bias leads to a phenomenon kn…
Sheaf Neural Networks with Connection Laplacians
Federico Barbero, Cristian Bodnar, Haitz Sáez de Ocáriz Borde +3
A Sheaf Neural Network (SNN) is a type of Graph Neural Network (GNN) that operates on a sheaf, an object that equips a graph with vector spaces over its nodes and edges and linear…
Simplicial Attention Networks
Christopher Wei Jin Goh, Cristian Bodnar, Pietro Liò
Graph representation learning methods have mostly been limited to the modelling of node-wise interactions. Recently, there has been an increased interest in understanding how highe…
Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs
Cristian Bodnar, Francesco Di Giovanni, Benjamin Paul Chamberlain +2
Cellular sheaves equip graphs with a "geometrical" structure by assigning vector spaces and linear maps to nodes and edges. Graph Neural Networks (GNNs) implicitly assume a graph w…
Weisfeiler and Lehman Go Cellular: CW Networks
Cristian Bodnar, Fabrizio Frasca, Nina Otter +4
Graph Neural Networks (GNNs) are limited in their expressive power, struggle with long-range interactions and lack a principled way to model higher-order structures. These problems…
Neural ODE Processes
Alexander Norcliffe, Cristian Bodnar, Ben Day +2
Neural Ordinary Differential Equations (NODEs) use a neural network to model the instantaneous rate of change in the state of a system. However, despite their apparent suitability…
Weisfeiler and Lehman Go Topological: Message Passing Simplicial Networks
Cristian Bodnar, Fabrizio Frasca, Yu Guang Wang +4
The pairwise interaction paradigm of graph machine learning has predominantly governed the modelling of relational systems. However, graphs alone cannot capture the multi-level int…
The Role of Isomorphism Classes in Multi-Relational Datasets
Vijja Wichitwechkarn, Ben Day, Cristian Bodnar +2
Multi-interaction systems abound in nature, from colloidal suspensions to gene regulatory circuits. These systems can produce complex dynamics and graph neural networks have been p…
On Second Order Behaviour in Augmented Neural ODEs
Alexander Norcliffe, Cristian Bodnar, Ben Day +2
Neural Ordinary Differential Equations (NODEs) are a new class of models that transform data continuously through infinite-depth architectures. The continuous nature of NODEs has m…
Deep Graph Mapper: Seeing Graphs through the Neural Lens
Cristian Bodnar, Cătălina Cangea, Pietro Liò
Recent advancements in graph representation learning have led to the emergence of condensed encodings that capture the main properties of a graph. However, even though these abstra…
Proximal Distilled Evolutionary Reinforcement Learning
Cristian Bodnar, Ben Day, Pietro Lió
Reinforcement Learning (RL) has achieved impressive performance in many complex environments due to the integration with Deep Neural Networks (DNNs). At the same time, Genetic Algo…