Welcome

Hi! Welcome to the website of the graph representation learning reading group at Mila - Quebec AI Institute. We cover papers on a wide range of topics, spanning theory, methods, and (industrial) applications.

Feel free to join us (Zoom link) and discuss research at the intersection of graphs and machine learning!

Upcoming talks

Graph Learning reading group is back for Winter2022 semester! Now in new default time slot: Thursdays @11am ET. However the meeting time may change on individual bases to accommodate our speaker.

Upcoming and past talks of this semester are listed below. If possible, we will make slides and video recordings available after the talk.

Date (Eastern Time) Presenter Topic Materials
Thur, Jan 20, 2022 @11:00am ET Boris Knyazev, Samsung AI Parameter Prediction for Unseen Deep Architectures [paper] [video]
Thur, Feb 3, 2022 @11:00am ET Aleksandar Bojchevski, Helmholtz Center Trustworthy Machine Learning for Graphs with Guarantees [1] [2] [3] [video]
Thur, Feb 10, 2022 no meeting
Thur, Feb 17, 2022 @11:00am ET Elias Khalil, U of Toronto Graph Neural Networks in Discrete Optimization — some recent use cases [1] [2] [video]
Thur, Feb 24, 2022 @11:00am ET Shengchao Liu, Mila Pre-Training Molecular Graph Representation With 3D Geometry – Rethinking Self-Supervised Learning on Structured Data [1] [video]
Thur, Mar 3, 2022 @noon ET Weihua Hu, Stanford Open Graph Benchmark Large-Scale Challenge [1] [2] [video]
Thur, Mar 17, 2022 @11:00am ET Meng Qu, Mila Neural Structured Prediction for Inductive Node Classification [1] [video]
Thur, Mar 31, 2022 @11:00am ET Ana Lucic and Maartje ter Hoeve, UvA CF-GNNExplainer: Counterfactual Explanations for Graph Neural Networks [1] [video]
Thur, Apr 14, 2022 @9:30am ET Jungtaek Kim, POSTECH Brick-by-Brick: Combinatorial Construction with Deep Reinforcement Learning [1] [video]

Archive of past talks

Past talks from previous semester(s).

Date (Eastern Time) Presenter Topic Materials
September 23, 2021 @ 4:00 PM RG Organizers Design Space for Graph Neural Networks [paper]
October 7, 2021 @ 4:00 PM Alexander Tong, Yale University Diffusion Earth Mover’s Distance on graphs [1] [2] [video]
October 14, 2021 @ 4:00 PM Dominique Beaini, Valence Discovery Unlocking Deep Learning for Graphs [SAN] [DGN] [PNA] [video]
October 21, 2021 @ 10:30 AM Benedek Rozemberczki, AstraZeneca PyTorch Geometric Temporal: Spatiotemporal Signal Processing with Neural Machine Learning Models [paper] [video]
October 28, 2021 @ 10:00 AM Petar Veličković, DeepMind Neuralising a Computer Scientist: The Story So Far [paper] [video]
November 4, 2021 @ 10:00 AM Matthias Fey, TU Dortmund University Pytorch Geometric 2.0 and Auto-Scaling GNNs [paper] [video]
November 11, 2021 @ 4:00 PM Uri Alon, Carnegie Mellon University How Attentive are Graph Attention Networks? [paper] [video]
November 18, 2021 @ 10:15 AM Bastian Rieck, Helmholtz Centre Munich Learning Topology-Based Graph Representations [1] [2] [3] [video]
November 25, 2021 @ 4:00 PM Joey Bose, Mila & McGill Introduction to Equivariant GNNs [Tensor Field Nets] [Schnet] [EGNN] [PAINN] [GemNet] [SpinConv] [video]
December 2, 2021 @ 10:00 AM Johannes Klicpera, Technical University of Munich Incorporating Directionality in GNNs [DimeNet] [GemNet] [Synthetic coordinates] [video]

Contact

If you are interested in presenting your work in the reading group, please reach out to one of the organizers listed above.