101 citations · 391 across the 23 of their papers we have counts for
23 papers
Locality-Aware Graph-Rewiring in GNNs
Federico Barbero, Ameya Velingker, Amin Saberi +2
Graph Neural Networks (GNNs) are popular models for machine learning on graphs that typically follow the message-passing paradigm, whereby the feature of a node is updated recursiv…
RetroBridge: Modeling Retrosynthesis with Markov Bridges
Ilia Igashov, Arne Schneuing, Marwin Segler +2
Retrosynthesis planning is a fundamental challenge in chemistry which aims at designing reaction pathways from commercially available starting materials to a target molecule. Each…
Artificial Intelligence for Science in Quantum, Atomistic, and Continuum Systems
Xuan Zhang, Limei Wang, Jacob Helwig +60
Advances in artificial intelligence (AI) are fueling a new paradigm of discoveries in natural sciences. Today, AI has started to advance natural sciences by improving, accelerating…
Temporal Graph Benchmark for Machine Learning on Temporal Graphs
Shenyang Huang, Farimah Poursafaei, Jacob Danovitch +7
We present the Temporal Graph Benchmark (TGB), a collection of challenging and diverse benchmark datasets for realistic, reproducible, and robust evaluation of machine learning mod…
On the Impact of Sample Size in Reconstructing Graph Signals
Baskaran Sripathmanathan, Xiaowen Dong, Michael Bronstein
Reconstructing a signal on a graph from observations on a subset of the vertices is a fundamental problem in the field of graph signal processing. It is often assumed that adding a…
How does over-squashing affect the power of GNNs?
Francesco Di Giovanni, T. Konstantin Rusch, Michael M. Bronstein +4
Graph Neural Networks (GNNs) are the state-of-the-art model for machine learning on graph-structured data. The most popular class of GNNs operate by exchanging information between…
DRew: Dynamically Rewired Message Passing with Delay
Benjamin Gutteridge, Xiaowen Dong, Michael Bronstein +1
Message passing neural networks (MPNNs) have been shown to suffer from the phenomenon of over-squashing that causes poor performance for tasks relying on long-range interactions. T…
From Latent Graph to Latent Topology Inference: Differentiable Cell Complex Module
Claudio Battiloro, Indro Spinelli, Lev Telyatnikov +3
Latent Graph Inference (LGI) relaxed the reliance of Graph Neural Networks (GNNs) on a given graph topology by dynamically learning it. However, most of LGI methods assume to have…
Edge Directionality Improves Learning on Heterophilic Graphs
Emanuele Rossi, Bertrand Charpentier, Francesco Di Giovanni +3
Graph Neural Networks (GNNs) have become the de-facto standard tool for modeling relational data. However, while many real-world graphs are directed, the majority of today's GNN mo…
A Survey on Oversmoothing in Graph Neural Networks
T. Konstantin Rusch, Michael M. Bronstein, Siddhartha Mishra
Node features of graph neural networks (GNNs) tend to become more similar with the increase of the network depth. This effect is known as over-smoothing, which we axiomatically def…
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…
Curvature Filtrations for Graph Generative Model Evaluation
Joshua Southern, Jeremy Wayland, Michael Bronstein +1
Graph generative model evaluation necessitates understanding differences between graphs on the distributional level. This entails being able to harness salient attributes of graphs…
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…
Structure-based Drug Design with Equivariant Diffusion Models
Arne Schneuing, Charles Harris, Yuanqi Du +10
Structure-based drug design (SBDD) aims to design small-molecule ligands that bind with high affinity and specificity to pre-determined protein targets. Generative SBDD methods lev…
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…
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…
Understanding and Extending Subgraph GNNs by Rethinking Their Symmetries
Fabrizio Frasca, Beatrice Bevilacqua, Michael M. Bronstein +1
Subgraph GNNs are a recent class of expressive Graph Neural Networks (GNNs) which model graphs as collections of subgraphs. So far, the design space of possible Subgraph GNN archit…
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…
Learning to Infer Structures of Network Games
Emanuele Rossi, Federico Monti, Yan Leng +2
Strategic interactions between a group of individuals or organisations can be modelled as games played on networks, where a player's payoff depends not only on their actions but al…
Graph-in-Graph (GiG): Learning interpretable latent graphs in non-Euclidean domain for biological and healthcare applications
Kamilia Mullakaeva, Luca Cosmo, Anees Kazi +3
Graphs are a powerful tool for representing and analyzing unstructured, non-Euclidean data ubiquitous in the healthcare domain. Two prominent examples are molecule property predict…
Provably Efficient Causal Model-Based Reinforcement Learning for Systematic Generalization
Mirco Mutti, Riccardo De Santi, Emanuele Rossi +3
In the sequential decision making setting, an agent aims to achieve systematic generalization over a large, possibly infinite, set of environments. Such environments are modeled as…
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…