Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Petar Veličković

Petar Veličković

University of Cambridge - Computer Laboratory

Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges


May 02, 2021
Michael M. Bronstein, Joan Bruna, Taco Cohen, Petar Veličković

* 156 pages. Work in progress -- comments welcome! 

  Access Paper or Ask Questions

Persistent Message Passing


Mar 01, 2021
Heiko Strathmann, Mohammadamin Barekatain, Charles Blundell, Petar Veličković

* 7 pages, 2 figures 

  Access Paper or Ask Questions

Combinatorial optimization and reasoning with graph neural networks


Feb 18, 2021
Quentin Cappart, Didier Chételat, Elias Khalil, Andrea Lodi, Christopher Morris, Petar Veličković


  Access Paper or Ask Questions

Bootstrapped Representation Learning on Graphs


Feb 12, 2021
Shantanu Thakoor, Corentin Tallec, Mohammad Gheshlaghi Azar, Rémi Munos, Petar Veličković, Michal Valko


  Access Paper or Ask Questions

Predicting Patient Outcomes with Graph Representation Learning


Jan 11, 2021
Emma Rocheteau, Catherine Tong, Petar Veličković, Nicholas Lane, Pietro Liò

* Accepted at the W3PHIAI-21 and DLG-AAAI'21 workshops at AAAI 2021 

  Access Paper or Ask Questions

A step towards neural genome assembly


Nov 10, 2020
Lovro Vrček, Petar Veličković, Mile Šikić

* NeurIPS 2020 Learning Meets Combinatorial Algorithms Workshop. 5 pages, 1 figure 

  Access Paper or Ask Questions

On the role of planning in model-based deep reinforcement learning


Nov 08, 2020
Jessica B. Hamrick, Abram L. Friesen, Feryal Behbahani, Arthur Guez, Fabio Viola, Sims Witherspoon, Thomas Anthony, Lars Buesing, Petar Veličković, Théophane Weber


  Access Paper or Ask Questions

XLVIN: eXecuted Latent Value Iteration Nets


Oct 25, 2020
Andreea Deac, Petar Veličković, Ognjen Milinković, Pierre-Luc Bacon, Jian Tang, Mladen Nikolić

* NeurIPS 2020 Deep Reinforcement Learning Workshop 

  Access Paper or Ask Questions

Hierachial Protein Function Prediction with Tails-GNNs


Jul 24, 2020
Stefan Spalević, Petar Veličković, Jovana Kovačević, Mladen Nikolić

* ICML 2020 - Workshops - Graph RepresGraph Representation Learning and Beyond (GRL+) 

  Access Paper or Ask Questions

Pointer Graph Networks


Jun 11, 2020
Petar Veličković, Lars Buesing, Matthew C. Overlan, Razvan Pascanu, Oriol Vinyals, Charles Blundell


  Access Paper or Ask Questions

Principal Neighbourhood Aggregation for Graph Nets


Apr 12, 2020
Gabriele Corso, Luca Cavalleri, Dominique Beaini, Pietro Liò, Petar Veličković


  Access Paper or Ask Questions

The PlayStation Reinforcement Learning Environment (PSXLE)


Dec 12, 2019
Carlos Purves, Cătălina Cangea, Petar Veličković


  Access Paper or Ask Questions

Neural Execution of Graph Algorithms


Oct 23, 2019
Petar Veličković, Rex Ying, Matilde Padovano, Raia Hadsell, Charles Blundell

* Under review as a conference paper at ICLR 2020. 13 pages, 4 figures 

  Access Paper or Ask Questions

Drug-Drug Adverse Effect Prediction with Graph Co-Attention


May 02, 2019
Andreea Deac, Yu-Hsiang Huang, Petar Veličković, Pietro Liò, Jian Tang

* 8 pages, 5 figures 

  Access Paper or Ask Questions

Spatio-Temporal Deep Graph Infomax


Apr 12, 2019
Felix L. Opolka, Aaron Solomon, Cătălina Cangea, Petar Veličković, Pietro Liò, R Devon Hjelm

* 6 pages, 2 figures, Representation Learning on Graphs and Manifolds Workshop of the International Conference on Learning Representations (ICLR) 

  Access Paper or Ask Questions

ChronoMID - Cross-Modal Neural Networks for 3-D Temporal Medical Imaging Data


Jan 12, 2019
Alexander G. Rakowski, Petar Veličković, Enrico Dall'Ara, Pietro Liò

* 8 pages, 7 figures, 2 tables 

  Access Paper or Ask Questions

Towards Sparse Hierarchical Graph Classifiers


Nov 03, 2018
Cătălina Cangea, Petar Veličković, Nikola Jovanović, Thomas Kipf, Pietro Liò

* To appear in the Workshop on Relational Representation Learning (R2L) at NIPS 2018. 6 pages, 3 figures 

  Access Paper or Ask Questions

Deep Graph Infomax


Sep 27, 2018
Petar Veličković, William Fedus, William L. Hamilton, Pietro Liò, Yoshua Bengio, R Devon Hjelm

* Under review as a conference paper at ICLR 2019. 15 pages, 8 figures 

  Access Paper or Ask Questions

Attentive cross-modal paratope prediction


Jun 12, 2018
Andreea Deac, Petar Veličković, Pietro Sormanni

* To appear at the 2018 ICML/IJCAI Workshop on Computational Biology. 5 pages, 6 figures 

  Access Paper or Ask Questions

Automatic Inference of Cross-modal Connection Topologies for X-CNNs


May 02, 2018
Laurynas Karazija, Petar Veličković, Pietro Liò

* 10 pages, 3 figures, 2 tables, to appear in ISNN 2018 

  Access Paper or Ask Questions

Graph Attention Networks


Feb 04, 2018
Petar Veličković, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Liò, Yoshua Bengio

* To appear at ICLR 2018. 12 pages, 2 figures 

  Access Paper or Ask Questions

Cross-modal Recurrent Models for Weight Objective Prediction from Multimodal Time-series Data


Nov 29, 2017
Petar Veličković, Laurynas Karazija, Nicholas D. Lane, Sourav Bhattacharya, Edgar Liberis, Pietro Liò, Angela Chieh, Otmane Bellahsen, Matthieu Vegreville

* To appear in NIPS ML4H 2017 and NIPS TSW 2017 

  Access Paper or Ask Questions

Quantifying the Effects of Enforcing Disentanglement on Variational Autoencoders


Nov 24, 2017
Momchil Peychev, Petar Veličković, Pietro Liò

* Accepted to the Workshop on Learning Disentangled Representations at the 31st Annual Conference on Neural Information Processing Systems (NIPS 2017), 5 pages, 2 figures 

  Access Paper or Ask Questions

X-CNN: Cross-modal Convolutional Neural Networks for Sparse Datasets


Oct 17, 2016
Petar Veličković, Duo Wang, Nicholas D. Lane, Pietro Liò

* To appear in the 7th IEEE Symposium Series on Computational Intelligence (IEEE SSCI 2016), 8 pages, 6 figures. Minor revisions, in response to reviewers' comments 

  Access Paper or Ask Questions