188 citations · 667 across the 24 of their papers we have counts for
25 papers
Hyperbolic Deep Reinforcement Learning
Edoardo Cetin, Benjamin Chamberlain, Michael Bronstein +1
We propose a new class of deep reinforcement learning (RL) algorithms that model latent representations in hyperbolic space. Sequential decision-making requires reasoning about the…
Gradient Gating for Deep Multi-Rate Learning on Graphs
T. Konstantin Rusch, Benjamin P. Chamberlain, Michael W. Mahoney +2
We present Gradient Gating (G), a novel framework for improving the performance of Graph Neural Networks (GNNs). Our framework is based on gating the output of GNN layers with…
Graph Neural Networks for Link Prediction with Subgraph Sketching
Benjamin Paul Chamberlain, Sergey Shirobokov, Emanuele Rossi +5
Many Graph Neural Networks (GNNs) perform poorly compared to simple heuristics on Link Prediction (LP) tasks. This is due to limitations in expressive power such as the inability t…
Understanding convolution on graphs via energies
Francesco Di Giovanni, James Rowbottom, Benjamin P. Chamberlain +2
Graph Neural Networks (GNNs) typically operate by message-passing, where the state of a node is updated based on the information received from its neighbours. Most message-passing…
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…
Graph-Coupled Oscillator Networks
T. Konstantin Rusch, Benjamin P. Chamberlain, James Rowbottom +2
We propose Graph-Coupled Oscillator Networks (GraphCON), a novel framework for deep learning on graphs. It is based on discretizations of a second-order system of ordinary differen…