309 citations · 1.2k across the 38 of their papers we have counts for
40 papers
Half-Hop: A graph upsampling approach for slowing down message passing
Mehdi Azabou, Venkataramana Ganesh, Shantanu Thakoor +6
Message passing neural networks have shown a lot of success on graph-structured data. However, there are many instances where message passing can lead to over-smoothing or fail whe…
Geometric Epitope and Paratope Prediction
Marco Pegoraro, Clémentine Dominé, Emanuele Rodolà +2
Antibody-antigen interactions play a crucial role in identifying and neutralizing harmful foreign molecules. In this paper, we investigate the optimal representation for predicting…
Parallel Algorithms Align with Neural Execution
Valerie Engelmayer, Dobrik Georgiev, Petar Veličković
Neural algorithmic reasoners are parallel processors. Teaching them sequential algorithms contradicts this nature, rendering a significant share of their computations redundant. Pa…
Recursive Algorithmic Reasoning
Jonas Jürß, Dulhan Jayalath, Petar Veličković
Learning models that execute algorithms can enable us to address a key problem in deep learning: generalizing to out-of-distribution data. However, neural networks are currently un…
Dual Algorithmic Reasoning
Danilo Numeroso, Davide Bacciu, Petar Veličković
Neural Algorithmic Reasoning is an emerging area of machine learning which seeks to infuse algorithmic computation in neural networks, typically by training neural models to approx…
Everything is Connected: Graph Neural Networks
Petar Veličković
In many ways, graphs are the main modality of data we receive from nature. This is due to the fact that most of the patterns we see, both in natural and artificial systems, are ele…
Time-Warping Invariant Quantum Recurrent Neural Networks via Quantum-Classical Adaptive Gating
Ivana Nikoloska, Osvaldo Simeone, Leonardo Banchi +1
Adaptive gating plays a key role in temporal data processing via classical recurrent neural networks (RNN), as it facilitates retention of past information necessary to predict the…
Learnable Commutative Monoids for Graph Neural Networks
Euan Ong, Petar Veličković
Graph neural networks (GNNs) have been shown to be highly sensitive to the choice of aggregation function. While summing over a node's neighbours can approximate any permutation-in…
Learning to Configure Computer Networks with Neural Algorithmic Reasoning
Luca Beurer-Kellner, Martin Vechev, Laurent Vanbever +1
We present a new method for scaling automatic configuration of computer networks. The key idea is to relax the computationally hard search problem of finding a configuration that s…
Expander Graph Propagation
Andreea Deac, Marc Lackenby, Petar Veličković
Deploying graph neural networks (GNNs) on whole-graph classification or regression tasks is known to be challenging: it often requires computing node features that are mindful of b…
Affinity-Aware Graph Networks
Ameya Velingker, Ali Kemal Sinop, Ira Ktena +2
Graph Neural Networks (GNNs) have emerged as a powerful technique for learning on relational data. Owing to the relatively limited number of message passing steps they perform -- a…
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…
Utility of Equivariant Message Passing in Cortical Mesh Segmentation
Dániel Unyi, Ferdinando Insalata, Petar Veličković +1
The automated segmentation of cortical areas has been a long-standing challenge in medical image analysis. The complex geometry of the cortex is commonly represented as a polygon m…
Graph Neural Networks are Dynamic Programmers
Andrew Dudzik, Petar Veličković
Recent advances in neural algorithmic reasoning with graph neural networks (GNNs) are propped up by the notion of algorithmic alignment. Broadly, a neural network will be better at…
Towards combinatorial invariance for Kazhdan-Lusztig polynomials
Charles Blundell, Lars Buesing, Alex Davies +2
Kazhdan-Lusztig polynomials are important and mysterious objects in representation theory. Here we present a new formula for their computation for symmetric groups based on the Bru…
How to transfer algorithmic reasoning knowledge to learn new algorithms?
Louis-Pascal A. C. Xhonneux, Andreea Deac, Petar Velickovic +1
Learning to execute algorithms is a fundamental problem that has been widely studied. Prior work~\cite{veli19neural} has shown that to enable systematic generalisation on graph alg…
Relating Graph Neural Networks to Structural Causal Models
Matej Zečević, Devendra Singh Dhami, Petar Veličković +1
Causality can be described in terms of a structural causal model (SCM) that carries information on the variables of interest and their mechanistic relations. For most processes of…
Reasoning-Modulated Representations
Petar Veličković, Matko Bošnjak, Thomas Kipf +4
Neural networks leverage robust internal representations in order to generalise. Learning them is difficult, and often requires a large training set that covers the data distributi…
Neural Algorithmic Reasoning
Petar Veličković, Charles Blundell
Algorithms have been fundamental to recent global technological advances and, in particular, they have been the cornerstone of technical advances in one field rapidly being applied…
Persistent Message Passing
Heiko Strathmann, Mohammadamin Barekatain, Charles Blundell +1
Graph neural networks (GNNs) are a powerful inductive bias for modelling algorithmic reasoning procedures and data structures. Their prowess was mainly demonstrated on tasks featur…
Combinatorial optimization and reasoning with graph neural networks
Quentin Cappart, Didier Chételat, Elias Khalil +3
Combinatorial optimization is a well-established area in operations research and computer science. Until recently, its methods have focused on solving problem instances in isolatio…
Large-Scale Representation Learning on Graphs via Bootstrapping
Shantanu Thakoor, Corentin Tallec, Mohammad Gheshlaghi Azar +5
Self-supervised learning provides a promising path towards eliminating the need for costly label information in representation learning on graphs. However, to achieve state-of-the-…
Predicting Patient Outcomes with Graph Representation Learning
Emma Rocheteau, Catherine Tong, Petar Veličković +2
Recent work on predicting patient outcomes in the Intensive Care Unit (ICU) has focused heavily on the physiological time series data, largely ignoring sparse data such as diagnose…
A step towards neural genome assembly
Lovro Vrček, Petar Veličković, Mile Šikić
De novo genome assembly focuses on finding connections between a vast amount of short sequences in order to reconstruct the original genome. The central problem of genome assembly…