no code implementations • 20 May 2024 • Cristian Bodnar, Wessel P. Bruinsma, Ana Lucic, Megan Stanley, Anna Vaughan, Johannes Brandstetter, Patrick Garvan, Maik Riechert, Jonathan A. Weyn, Haiyu Dong, Jayesh K. Gupta, Kit Thambiratnam, Alexander T. Archibald, Chun-Chieh Wu, Elizabeth Heider, Max Welling, Richard E. Turner, Paris Perdikaris
Reliable forecasts of the Earth system are crucial for human progress and safety from natural disasters.
no code implementations • 9 Nov 2023 • Jialin Chen, Yuelin Wang, Cristian Bodnar, Rex Ying, Pietro Lio, Yu Guang Wang
However, recursively aggregating neighboring information with graph convolutions leads to indistinguishable node features in deep layers, which is known as the over-smoothing issue.
1 code implementation • 6 Jun 2023 • Lorenzo Giusti, Teodora Reu, Francesco Ceccarelli, Cristian Bodnar, Pietro Liò
Our message passing scheme accounts for the aforementioned limitations by letting the cells to receive also lower messages within each layer.
Ranked #1 on
Graph Classification
on HIV dataset
1 code implementation • 23 Jan 2023 • Chaitanya K. Joshi, Cristian Bodnar, Simon V. Mathis, Taco Cohen, Pietro Liò
The expressive power of Graph Neural Networks (GNNs) has been studied extensively through the Weisfeiler-Leman (WL) graph isomorphism test.
1 code implementation • 17 Jun 2022 • Federico Barbero, Cristian Bodnar, Haitz Sáez de Ocáriz Borde, Michael Bronstein, Petar Veličković, Pietro Liò
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 maps between these spaces.
Ranked #10 on
Node Classification
on Wisconsin
1 code implementation • 20 Apr 2022 • Christopher Wei Jin Goh, Cristian Bodnar, Pietro Liò
Leveraging the success of attention mechanisms in structured domains, we propose Simplicial Attention Networks (SAT), a new type of simplicial network that dynamically weighs the interactions between neighbouring simplicies and can readily adapt to novel structures.
1 code implementation • 9 Feb 2022 • Cristian Bodnar, Francesco Di Giovanni, Benjamin Paul Chamberlain, Pietro Liò, Michael M. Bronstein
In this paper, we use cellular sheaf theory to show that the underlying geometry of the graph is deeply linked with the performance of GNNs in heterophilic settings and their oversmoothing behaviour.
no code implementations • NeurIPS Workshop DLDE 2021 • Alexander Luke Ian Norcliffe, Cristian Bodnar, Ben Day, Nikola Simidjievski, Pietro Lio
In Norcliffe et al.[13], we discussed and systematically analysed how Neural ODEs (NODEs) can learn higher-order order dynamics.
1 code implementation • NeurIPS Workshop DLDE 2021 • Alexander Luke Ian Norcliffe, Cristian Bodnar, Ben Day, Jacob Moss, Pietro Lio
To this end, we introduce Neural ODE Processes (NDPs), a new class of stochastic processes determined by a distribution over Neural ODEs.
2 code implementations • NeurIPS 2021 • Cristian Bodnar, Fabrizio Frasca, Nina Otter, Yu Guang Wang, Pietro Liò, Guido Montúfar, Michael Bronstein
Nevertheless, these models can be severely constrained by the rigid combinatorial structure of Simplicial Complexes (SCs).
Ranked #1 on
Graph Regression
on ZINC 100k
2 code implementations • ICLR 2021 • Alexander Norcliffe, Cristian Bodnar, Ben Day, Jacob Moss, Pietro Liò
To address these problems, we introduce Neural ODE Processes (NDPs), a new class of stochastic processes determined by a distribution over Neural ODEs.
2 code implementations • ICLR Workshop GTRL 2021 • Cristian Bodnar, Fabrizio Frasca, Yu Guang Wang, Nina Otter, Guido Montúfar, Pietro Liò, Michael Bronstein
The pairwise interaction paradigm of graph machine learning has predominantly governed the modelling of relational systems.
no code implementations • 14 Nov 2020 • Cristian Bodnar, Karol Hausman, Gabriel Dulac-Arnold, Rico Jonschkowski
One of the most challenging aspects of real-world reinforcement learning (RL) is the multitude of unpredictable and ever-changing distractions that could divert an agent from what was tasked to do in its training environment.
no code implementations • 30 Sep 2020 • Vijja Wichitwechkarn, Ben Day, Cristian Bodnar, Matthew Wales, Pietro Liò
The current training and evaluation procedures for these models through the use of synthetic multi-relational datasets however are agnostic to interaction network isomorphism classes, which produce identical dynamics up to initial conditions.
1 code implementation • NeurIPS 2020 • Alexander Norcliffe, Cristian Bodnar, Ben Day, Nikola Simidjievski, Pietro Liò
Neural Ordinary Differential Equations (NODEs) are a new class of models that transform data continuously through infinite-depth architectures.
Ranked #22 on
Image Classification
on MNIST
1 code implementation • NeurIPS Workshop TDA_and_Beyond 2020 • 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.
no code implementations • 1 Oct 2019 • Cristian Bodnar, Adrian Li, Karol Hausman, Peter Pastor, Mrinal Kalakrishnan
The absence of an actor in Q2-Opt allows us to directly draw a parallel to the previous discrete experiments in the literature without the additional complexities induced by an actor-critic architecture.
1 code implementation • 24 Jun 2019 • Cristian Bodnar, Ben Day, Pietro Lió
We propose a novel algorithm called Proximal Distilled Evolutionary Reinforcement Learning (PDERL) that is characterised by a hierarchical integration between evolution and learning.
no code implementations • 2 May 2018 • Cristian Bodnar
Then, I show how the novel loss function of Wasserstein GAN-CLS can be used in a Conditional Progressive Growing GAN.