ELLIS Workshop
This workshop is part of the ELLIS program on Geometric Deep Learning. For more information on the European Lab for Learning and Intelligent Systems (ELLIS) visit https://ellis.eu/.
Recordings of invited talks are now available — see program below.
This workshop aims to bring together researchers and practicioners from the emerging fields of Graph Representation Learning and Geometric Deep Learning. The workshop will feature invited talks and a poster session. There will be ample opportunity for discussion and networking.
Speakers
- Peter Battaglia, DeepMind
- Natalia Neverova, Facebook AI Research (FAIR)
- Stephan Günnemann, TU Munich
- Yaron Lipman, Weizmann Institute of Science
- Miltos Allamanis, Microsoft Research
- Qi Liu, University of Oxford
- Pim de Haan, University of Amsterdam & Qualcomm AI Research
- Noemi Montobbio, Italian Institute of Technology
Accepted Papers
* denotes equal contribution.
- Emanuele Rossi, Fabrizio Frasca, Ben Chamberlain, Davide Eynard, Michael Bronstein, Federico Monti:
SIGN: Scalable Inception Graph Neural Networks [video, paper] - Nicolas Keriven, Gabriel Peyré:
Universal Invariant and Equivariant Graph Neural Networks [video, paper] - Felix L. Opolka, Pietro Liò:
Graph Convolutional Gaussian Processes For Link Prediction [video, paper] - Gabriele Corso*, Luca Cavalleri*, Dominique Beaini, Pietro Liò, Petar Veličković:
Principal Neighbourhood Aggregation for Graph Nets [video, paper, code] - Cristian Bodnar*, Cătălina Cangea*, Pietro Liò:
Deep Graph Mapper: Seeing Graphs through the Neural Lens [video, paper, code] - Devanshu Arya, Stevan Rudinac, Marcel Worring:
HyperLearn: A Distributed Approach for Representation Learning in Datasets With Many Modalities [video, paper] - Max Kochurov, Serge Kozlukov, Rasul Karimov:
Geoopt: Riemannian Adaptive Optimization Methods in PyTorch [paper, code] - Pietro Astolfi, Ruben Verhagen, Laurent Petit, Emanuele Olivetti, Jonathan Masci, Davide Boscaini, Paolo Avesani:
A geometric deep learning model to filter out anatomically non plausible fibers from tractograms [video, paper] - Davide Buffelli, Fabio Vandin:
Are Graph Convolutional Networks Fully Exploiting Graph Structure? [video] - Sephora Madjiheurem, Laura Toni:
State2vec: Off-Policy Successor Feature Approximators [paper] - Fatma Guney:
Learning Object-Object Relations in Video - Charlotte Bunne, David Alvarez-Melis, Andreas Krause, Stefanie Jegelka:
Learning Generative Models across Incomparable Spaces [paper, code] - Clément Vignac, Andreas Loukas, Pascal Frossard:
SMP: An Equivariant Message Passing Scheme for Learning Graph Structural Information [video] - Ivana Balazevic, Carl Allen, Timothy Hospedales:
Multi-relational Poincaré Graph Embeddings [video, paper, code] - Carl Allen*, Ivana Balazevic*, Timothy Hospedales:
On Understanding Knowledge Graph Representation [video, paper] - Vijja Wichitwechkarn, Ben Day, Cristian Bodnar, Pietro Liò:
Isomorphism Leakage in Multi-Interaction Datasets [video] - Riccardo Marin, Arianna Rampini, Umberto Castellani, Emanuele Rodolà, Maks Ovsjanikov, Simone Melzi:
Instant recovery of shape from spectrum via latent space connections [video, paper] - Janosch Menke, Oliver Koch:
Evaluation of Molecular Fingerprints for Similarity-based Virtual Screening generated through Graph Convolution Networks - David W. Romero, Erik J. Bekkers, Jakub M. Tomczak, Mark Hoogendoorn:
Attentive Group Equivariant Convolutional Networks [video, paper]
Program
Recordings of invited talks are now available — see below.
| Time | Presenter |
|---|---|
| 9.20-9.30 | Opening remarks (Thomas Kipf) |
| 9.30-10.00 | Peter Battaglia: Learning Physics with Graph Neural Networks [video] |
| 10.00-10.30 | Natalia Neverova: Entity-level Video Understanding [video] |
| 10.30-11.00 | Break & networking (topic-specific breakout rooms) |
| 11.00-11.30 | Stephan Günnemann: Adversarial Robustness of Machine Learning Models for Graphs [video] |
| 11.30-12.00 | Yaron Lipman: Deep Learning of Irregular and Geometric Data [video] |
| 12.00-12.15 | Qi Liu: Hyperbolic Graph Neural Networks [video] |
| 12.15-13.30 | Lunch & networking (topic-specific breakout rooms) |
| 13.30-14.00 | Miltos Allamanis: Typilus: Neural Type Hints [video] |
| 14.00-14.15 | Noemi Montobbio: KerCNNs: Biologically Inspired Lateral Connections for Classification of Corrupted Images [video] |
| 14.15-14.30 | Pim de Haan: Natural Graph Convolutions [video] |
| 14.30-15.00 | Break & networking (topic-specific breakout rooms) |
| 15.00-15.30 | Poster spotlights (1min pre-recorded video per poster) |
| 15.30-17.00 | Poster session / networking in breakout rooms |
Organizers
This workshop is organized by:
- Thomas Kipf, Google Research Amsterdam
- Erik Bekkers, University of Amsterdam
- Félice Arends, University of Amsterdam
- Michael Bronstein, Imperial College & Twitter
- Max Welling, University of Amsterdam & Qualcomm AI Research