GraphML News (March 30th) - AlphaFold course, Upcoming Summer Schools

The first week of ICML rebuttals has passed, one week to go - good luck everyone 💪

EMBL-EBI together with Google DeepMind released a free entry-level course about the basics of protein folding and using AlphaFold for structure prediction. The course helps to understand inputs and outputs of AlphaFold, how to interpret the metrics and predictions, and a bit of more advanced usage.

A handful of summer schools covering lots of Graph and Geometric DL were announced recently:

- Eastern European ML Summer School | 15-20 July 2024, Novi Sad, Serbia
- ELLIS Summer School on Machine Learning for Healthcare and Biology | 11-13 June 2024, Manchester, UK
- Generative Modeling Summer School | 24-28th June 2024, Eindhoven, Netherlands
- The workshop on mining and learning with graphs (MLG) will be co-located with ECML PKDD in Vilnius, Lithuania in September 2024 featuring keynotes by Yllka Velaj and Haggai Maron.

Weekend reading:

A new version of the Hitchhiker’s guide on Geometric GNNs featuring frame-based invariant GNNs and unconstrained GNNs (btw, the paper will be presented at the next LoGaG reading group on Monday, April 1st)

Space Group Informed Transformer for Crystalline Materials Generation - autoregressive, transformer-based crystal generation that takes into account space groups and Wyckoff positions (a competing diffusion model DiffCSP++ was accepted at ICLR’24)

Graphs Generalization under Distribution Shifts by Tian et al

Addressing heterophily in node classification with graph echo state networks by Alessio Micheli and Domenico Tortorella — applies a reservoir computing approach, that is, randomly initialize GNN weights to obtain a desired Lipschitz constant