You need to log in to edit.

You can create a new account if you don't have one.

Or, discuss a change on Slack.

You can create a new account if you don't have one.

Or, discuss a change on Slack.

no code implementations • 23 Feb 2024 • Bruno Gavranović, Paul Lessard, Andrew Dudzik, Tamara von Glehn, João G. M. Araújo, Petar Veličković

We present our position on the elusive quest for a general-purpose framework for specifying and studying deep learning architectures.

no code implementations • 14 Feb 2024 • Theodore Papamarkou, Tolga Birdal, Michael Bronstein, Gunnar Carlsson, Justin Curry, Yue Gao, Mustafa Hajij, Roland Kwitt, Pietro Liò, Paolo Di Lorenzo, Vasileios Maroulas, Nina Miolane, Farzana Nasrin, Karthikeyan Natesan Ramamurthy, Bastian Rieck, Simone Scardapane, Michael T. Schaub, Petar Veličković, Bei Wang, Yusu Wang, Guo-Wei Wei, Ghada Zamzmi

Topological deep learning (TDL) is a rapidly evolving field that uses topological features to understand and design deep learning models.

no code implementations • 6 Nov 2023 • Abbas Mehrabian, Ankit Anand, Hyunjik Kim, Nicolas Sonnerat, Matej Balog, Gheorghe Comanici, Tudor Berariu, Andrew Lee, Anian Ruoss, Anna Bulanova, Daniel Toyama, Sam Blackwell, Bernardino Romera Paredes, Petar Veličković, Laurent Orseau, Joonkyung Lee, Anurag Murty Naredla, Doina Precup, Adam Zsolt Wagner

This work studies a central extremal graph theory problem inspired by a 1975 conjecture of Erd\H{o}s, which aims to find graphs with a given size (number of nodes) that maximize the number of edges without having 3- or 4-cycles.

no code implementations • 16 Oct 2023 • Zhe Wang, Petar Veličković, Daniel Hennes, Nenad Tomašev, Laurel Prince, Michael Kaisers, Yoram Bachrach, Romuald Elie, Li Kevin Wenliang, Federico Piccinini, William Spearman, Ian Graham, Jerome Connor, Yi Yang, Adrià Recasens, Mina Khan, Nathalie Beauguerlange, Pablo Sprechmann, Pol Moreno, Nicolas Heess, Michael Bowling, Demis Hassabis, Karl Tuyls

The utility of TacticAI is validated by a qualitative study conducted with football domain experts at Liverpool FC.

1 code implementation • 17 Aug 2023 • Mehdi Azabou, Venkataramana Ganesh, Shantanu Thakoor, Chi-Heng Lin, Lakshmi Sathidevi, Ran Liu, Michal Valko, Petar Veličković, Eva L. Dyer

Message passing neural networks have shown a lot of success on graph-structured data.

Ranked #1 on Node Classification on AMZ Comp

no code implementations • 18 Jul 2023 • Rishabh Jain, Petar Veličković, Pietro Liò

Graph Neural Networks (GNNs) have shown considerable success in neural algorithmic reasoning.

Ranked #19 on Graph Regression on Peptides-struct

1 code implementation • 17 Jul 2023 • Vladimir V. Mirjanić, Razvan Pascanu, Petar Veličković

Neural Algorithmic Reasoning (NAR) is a research area focused on designing neural architectures that can reliably capture classical computation, usually by learning to execute algorithms.

no code implementations • 8 Jul 2023 • Valerie Engelmayer, Dobrik Georgiev, Petar Veličković

Neural algorithmic reasoners are parallel processors.

1 code implementation • 1 Jul 2023 • 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.

no code implementations • 27 Jun 2023 • Andrew Dudzik, Tamara von Glehn, Razvan Pascanu, Petar Veličković

In this work, we explicitly separate the concepts of node state update and message function invocation.

no code implementations • 6 Jun 2023 • Francesco Di Giovanni, T. Konstantin Rusch, Michael M. Bronstein, Andreea Deac, Marc Lackenby, Siddhartha Mishra, Petar Veličković

In this paper, we provide a rigorous analysis to determine which function classes of node features can be learned by an MPNN of a given capacity.

no code implementations • 28 May 2023 • Marco Pegoraro, Clémentine Dominé, Emanuele Rodolà, Petar Veličković, Andreea Deac

Antibody-antigen interactions play a crucial role in identifying and neutralizing harmful foreign molecules.

no code implementations • 20 Feb 2023 • Beatrice Bevilacqua, Kyriacos Nikiforou, Borja Ibarz, Ioana Bica, Michela Paganini, Charles Blundell, Jovana Mitrovic, Petar Veličković

We evaluate our method on the CLRS algorithmic reasoning benchmark, where we show up to 3$\times$ improvements on the OOD test data.

no code implementations • 9 Feb 2023 • Danilo Numeroso, Davide Bacciu, Petar Veličković

We demonstrate that simultaneously learning the dual definition of these optimisation problems in algorithmic learning allows for better learning and qualitatively better solutions.

no code implementations • 19 Jan 2023 • Ivana Nikoloska, Osvaldo Simeone, Leonardo Banchi, Petar Veličković

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 future, providing a mechanism that preserves invariance to time warping transformations.

no code implementations • 19 Jan 2023 • Petar Veličković

In many ways, graphs are the main modality of data we receive from nature.

no code implementations • 16 Dec 2022 • Euan Ong, Petar Veličković

And with this, we construct an aggregator of $O(\log V)$ depth, yielding exponential improvements for both parallelism and dependency length while achieving performance competitive with recurrent aggregators.

no code implementations • Learning on Graphs 2022 • Michal Pándy, Weikang Qiu, Gabriele Corso, Petar Veličković, Rex Ying, Jure Leskovec, Pietro Liò

At training time, we aggregate datasets of search trajectories and ground-truth shortest path distances, which we use to train a specialized graph neural network-based heuristic function using backpropagation through steps of the pathfinding process.

no code implementations • 29 Nov 2022 • Yu He, Petar Veličković, Pietro Liò, Andreea Deac

Neural algorithmic reasoning studies the problem of learning algorithms with neural networks, especially with graph architectures.

no code implementations • 26 Oct 2022 • Luca Beurer-Kellner, Martin Vechev, Laurent Vanbever, Petar Veličković

We present a new method for scaling automatic configuration of computer networks.

no code implementations • 6 Oct 2022 • 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 both local interactions in their neighbourhood and the global context of the graph structure.

2 code implementations • 22 Sep 2022 • Borja Ibarz, Vitaly Kurin, George Papamakarios, Kyriacos Nikiforou, Mehdi Bennani, Róbert Csordás, Andrew Dudzik, Matko Bošnjak, Alex Vitvitskyi, Yulia Rubanova, Andreea Deac, Beatrice Bevilacqua, Yaroslav Ganin, Charles Blundell, Petar Veličković

The cornerstone of neural algorithmic reasoning is the ability to solve algorithmic tasks, especially in a way that generalises out of distribution.

no code implementations • 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 #6 on Node Classification on Wisconsin

1 code implementation • 7 Jun 2022 • Dániel Unyi, Ferdinando Insalata, Petar Veličković, Bálint Gyires-Tóth

Our evaluation shows that GNNs outperform EGNNs on aligned meshes, due to their ability to leverage the presence of a global coordinate system.

1 code implementation • 31 May 2022 • Petar Veličković, Adrià Puigdomènech Badia, David Budden, Razvan Pascanu, Andrea Banino, Misha Dashevskiy, Raia Hadsell, Charles Blundell

Learning representations of algorithms is an emerging area of machine learning, seeking to bridge concepts from neural networks with classical algorithms.

no code implementations • 11 Apr 2022 • Danilo Numeroso, Davide Bacciu, Petar Veličković

At training time, we exploit multi-task learning to learn jointly the Dijkstra's algorithm and a consistent heuristic function for the A* search algorithm.

no code implementations • 29 Mar 2022 • Andrew Dudzik, Petar Veličković

Recent advances in neural algorithmic reasoning with graph neural networks (GNNs) are propped up by the notion of algorithmic alignment.

no code implementations • 22 Feb 2022 • Petar Veličković

The message passing framework is the foundation of the immense success enjoyed by graph neural networks (GNNs) in recent years.

no code implementations • NeurIPS 2021 • Andreea Deac, Petar Veličković, Ognjen Milinković, Pierre-Luc Bacon, Jian Tang, Mladen Nikolić

We find that prior approaches either assume that the environment is provided in such a tabular form -- which is highly restrictive -- or infer "local neighbourhoods" of states to run value iteration over -- for which we discover an algorithmic bottleneck effect.

no code implementations • ICLR 2022 • Jonathan Godwin, Michael Schaarschmidt, Alexander L Gaunt, Alvaro Sanchez-Gonzalez, Yulia Rubanova, Petar Veličković, James Kirkpatrick, Peter Battaglia

We introduce “Noisy Nodes”, a very simple technique for improved training of GNNs, in which we corrupt the input graph with noise, and add a noise correcting node-level loss.

Initial Structure to Relaxed Energy (IS2RE), Direct
Molecular Property Prediction
**+1**

1 code implementation • NeurIPS 2021 • Gabriele Corso, Rex Ying, Michal Pándy, Petar Veličković, Jure Leskovec, Pietro Liò

The development of data-dependent heuristics and representations for biological sequences that reflect their evolutionary distance is critical for large-scale biological research.

no code implementations • 9 Sep 2021 • Matej Zečević, Devendra Singh Dhami, Petar Veličković, Kristian Kersting

Causality can be described in terms of a structural causal model (SCM) that carries information on the variables of interest and their mechanistic relations.

no code implementations • 25 Aug 2021 • Austin Derrow-Pinion, Jennifer She, David Wong, Oliver Lange, Todd Hester, Luis Perez, Marc Nunkesser, Seongjae Lee, Xueying Guo, Brett Wiltshire, Peter W. Battaglia, Vishal Gupta, Ang Li, Zhongwen Xu, Alvaro Sanchez-Gonzalez, Yujia Li, Petar Veličković

Travel-time prediction constitutes a task of high importance in transportation networks, with web mapping services like Google Maps regularly serving vast quantities of travel time queries from users and enterprises alike.

1 code implementation • 20 Jul 2021 • Ravichandra Addanki, Peter W. Battaglia, David Budden, Andreea Deac, Jonathan Godwin, Thomas Keck, Wai Lok Sibon Li, Alvaro Sanchez-Gonzalez, Jacklynn Stott, Shantanu Thakoor, Petar Veličković

In doing so, we demonstrate evidence of scalable self-supervised graph representation learning, and utility of very deep GNNs -- both very important open issues.

no code implementations • 19 Jul 2021 • Petar Veličković, Matko Bošnjak, Thomas Kipf, Alexander Lerchner, Raia Hadsell, Razvan Pascanu, Charles Blundell

Neural networks leverage robust internal representations in order to generalise.

1 code implementation • 15 Jul 2021 • Dobrik Georgiev, Pietro Barbiero, Dmitry Kazhdan, Petar Veličković, Pietro Liò

Recent research on graph neural network (GNN) models successfully applied GNNs to classical graph algorithms and combinatorial optimisation problems.

1 code implementation • 15 Jun 2021 • Jonathan Godwin, Michael Schaarschmidt, Alexander Gaunt, Alvaro Sanchez-Gonzalez, Yulia Rubanova, Petar Veličković, James Kirkpatrick, Peter Battaglia

From this observation we derive "Noisy Nodes", a simple technique in which we corrupt the input graph with noise, and add a noise correcting node-level loss.

Ranked #4 on Initial Structure to Relaxed Energy (IS2RE) on OC20

no code implementations • 31 May 2021 • Alice Del Vecchio, Andreea Deac, Pietro Liò, Petar Veličković

Antibodies are proteins in the immune system which bind to antigens to detect and neutralise them.

no code implementations • 6 May 2021 • 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 to another.

5 code implementations • 27 Apr 2021 • Michael M. Bronstein, Joan Bruna, Taco Cohen, Petar Veličković

The last decade has witnessed an experimental revolution in data science and machine learning, epitomised by deep learning methods.

no code implementations • ICLR Workshop GTRL 2021 • Shantanu Thakoor, Corentin Tallec, Mohammad Gheshlaghi Azar, Remi Munos, Petar Veličković, Michal Valko

Current state-of-the-art self-supervised learning methods for graph neural networks are based on contrastive learning.

no code implementations • ICLR Workshop GTRL 2021 • Heiko Strathmann, Mohammadamin Barekatain, Charles Blundell, Petar Veličković

Graph neural networks (GNNs) are a powerful inductive bias for modelling algorithmic reasoning procedures and data structures.

no code implementations • 18 Feb 2021 • Quentin Cappart, Didier Chételat, Elias Khalil, Andrea Lodi, Christopher Morris, Petar Veličković

Combinatorial optimization is a well-established area in operations research and computer science.

3 code implementations • ICLR 2022 • Shantanu Thakoor, Corentin Tallec, Mohammad Gheshlaghi Azar, Mehdi Azabou, Eva L. Dyer, Rémi Munos, Petar Veličković, Michal Valko

To address these challenges, we introduce Bootstrapped Graph Latents (BGRL) - a graph representation learning method that learns by predicting alternative augmentations of the input.

1 code implementation • 11 Jan 2021 • Emma Rocheteau, Catherine Tong, Petar Veličković, Nicholas Lane, Pietro Liò

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 diagnoses and medications.

1 code implementation • NeurIPS Workshop LMCA 2020 • 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.

no code implementations • ICLR 2021 • Jessica B. Hamrick, Abram L. Friesen, Feryal Behbahani, Arthur Guez, Fabio Viola, Sims Witherspoon, Thomas Anthony, Lars Buesing, Petar Veličković, Théophane Weber

These results indicate where and how to utilize planning in reinforcement learning settings, and highlight a number of open questions for future MBRL research.

Model-based Reinforcement Learning
reinforcement-learning
**+1**

no code implementations • 25 Oct 2020 • Andreea Deac, Petar Veličković, Ognjen Milinković, Pierre-Luc Bacon, Jian Tang, Mladen Nikolić

Value Iteration Networks (VINs) have emerged as a popular method to incorporate planning algorithms within deep reinforcement learning, enabling performance improvements on tasks requiring long-range reasoning and understanding of environment dynamics.

no code implementations • 24 Jul 2020 • Stefan Spalević, Petar Veličković, Jovana Kovačević, Mladen Nikolić

Protein function prediction may be framed as predicting subgraphs (with certain closure properties) of a directed acyclic graph describing the hierarchy of protein functions.

no code implementations • NeurIPS 2020 • Petar Veličković, Lars Buesing, Matthew C. Overlan, Razvan Pascanu, Oriol Vinyals, Charles Blundell

This static input structure is often informed purely by insight of the machine learning practitioner, and might not be optimal for the actual task the GNN is solving.

8 code implementations • NeurIPS 2020 • Gabriele Corso, Luca Cavalleri, Dominique Beaini, Pietro Liò, Petar Veličković

Graph Neural Networks (GNNs) have been shown to be effective models for different predictive tasks on graph-structured data.

Ranked #4 on Node Classification on PATTERN 100k

1 code implementation • 12 Dec 2019 • Carlos Purves, Cătălina Cangea, Petar Veličković

We propose a new benchmark environment for evaluating Reinforcement Learning (RL) algorithms: the PlayStation Learning Environment (PSXLE), a PlayStation emulator modified to expose a simple control API that enables rich game-state representations.

no code implementations • ICLR 2020 • Petar Veličković, Rex Ying, Matilde Padovano, Raia Hadsell, Charles Blundell

Graph Neural Networks (GNNs) are a powerful representational tool for solving problems on graph-structured inputs.

1 code implementation • 2 May 2019 • Andreea Deac, Yu-Hsiang Huang, Petar Veličković, Pietro Liò, Jian Tang

Complex or co-existing diseases are commonly treated using drug combinations, which can lead to higher risk of adverse side effects.

no code implementations • 12 Apr 2019 • Felix L. Opolka, Aaron Solomon, Cătălina Cangea, Petar Veličković, Pietro Liò, R. Devon Hjelm

Spatio-temporal graphs such as traffic networks or gene regulatory systems present challenges for the existing deep learning methods due to the complexity of structural changes over time.

no code implementations • 12 Jan 2019 • Alexander G. Rakowski, Petar Veličković, Enrico Dall'Ara, Pietro Liò

ChronoMID builds on the success of cross-modal convolutional neural networks (X-CNNs), making the novel application of the technique to medical imaging data.

1 code implementation • 3 Nov 2018 • Cătălina Cangea, Petar Veličković, Nikola Jovanović, Thomas Kipf, Pietro Liò

Recent advances in representation learning on graphs, mainly leveraging graph convolutional networks, have brought a substantial improvement on many graph-based benchmark tasks.

11 code implementations • ICLR 2019 • Petar Veličković, William Fedus, William L. Hamilton, Pietro Liò, Yoshua Bengio, R. Devon Hjelm

We present Deep Graph Infomax (DGI), a general approach for learning node representations within graph-structured data in an unsupervised manner.

Ranked #49 on Node Classification on Citeseer

no code implementations • 12 Jun 2018 • Andreea Deac, Petar Veličković, Pietro Sormanni

Antibodies are a critical part of the immune system, having the function of directly neutralising or tagging undesirable objects (the antigens) for future destruction.

1 code implementation • 2 May 2018 • Laurynas Karazija, Petar Veličković, Pietro Liò

The base approach learns the topology in a data-driven manner, by using measurements performed on the base CNN and supplied data.

1 code implementation • 24 Nov 2017 • Momchil Peychev, Petar Veličković, Pietro Liò

In this paper we quantify the effects of the parameter $\beta$ on the model performance and disentanglement.

90 code implementations • ICLR 2018 • Petar Veličković, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Liò, Yoshua Bengio

We present graph attention networks (GATs), novel neural network architectures that operate on graph-structured data, leveraging masked self-attentional layers to address the shortcomings of prior methods based on graph convolutions or their approximations.

Ranked #1 on Node Property Prediction on ogbn-proteins

no code implementations • 23 Sep 2017 • Petar Veličković, Laurynas Karazija, Nicholas D. Lane, Sourav Bhattacharya, Edgar Liberis, Pietro Liò, Angela Chieh, Otmane Bellahsen, Matthieu Vegreville

We analyse multimodal time-series data corresponding to weight, sleep and steps measurements.

1 code implementation • 2 Sep 2017 • Cătălina Cangea, Petar Veličković, Pietro Liò

Our work improves on existing multimodal deep learning algorithms in two essential ways: (1) it presents a novel method for performing cross-modality (before features are learned from individual modalities) and (2) extends the previously proposed cross-connections which only transfer information between streams that process compatible data.

no code implementations • 1 Oct 2016 • Petar Veličković, Duo Wang, Nicholas D. Lane, Pietro Liò

In this paper we propose cross-modal convolutional neural networks (X-CNNs), a novel biologically inspired type of CNN architectures, treating gradient descent-specialised CNNs as individual units of processing in a larger-scale network topology, while allowing for unconstrained information flow and/or weight sharing between analogous hidden layers of the network---thus generalising the already well-established concept of neural network ensembles (where information typically may flow only between the output layers of the individual networks).

Cannot find the paper you are looking for? You can
Submit a new open access paper.

Contact us on:
hello@paperswithcode.com
.
Papers With Code is a free resource with all data licensed under CC-BY-SA.