Post #775

GraphML News (June 10th) Emanuele Rossi and Michael Bronstein published a new blog post on Directed GNNs. The idea is rather simple (different learnable aggregations for in- and out- neighbors) and shows very good results on heterophilic graphs. In fact, DirGNNs very much resemble relational GNNs (R-GCN, CompGCN, NBFNet, and so on) who have learnable aggregations per unique relation type (and its inverse), and we recently published a theory paper on the expressiveness of such GNNs. Great to see prominent GNN folks joining the relational party 😉 The Learning on Graphs Conference (LoG) is not just one of the coolest venue for Graph ML research - the organizers do care about the community and factor in your feedback. Bastian Rieck and Corinna Coupette summarized the results from the anonymous poll among authors and reviewers in Evaluating the "Learning on Graphs" Conference Experience highlighting what worked (eg, monetary awards for reviewers and lesser paper load) and not quite (some papers were rejected even when authors submitted rebuttals but reviewers did not engage). Let’s help LoG to grow to the best Graph ML research venues! FAIR, CMU, and The Open Catalyst Project are about to announce the next large NeurIPS challenge - most likely it would be about adsorption energy estimation. Brace yourselves and prepare your best equivariant geometrics models. Da Zheng and Florian Saupe from AWS published a post introducing GraphStorm (we noticed the original paper a few weeks ago), a low-code framework for large-scale graph learning targeted for enterprise applications. The post goes through several examples on graph building and running inference. Some weekend reading: Ewald-based Long-Range Message Passing for Molecular Graphs (ICML’23) and its LOG2 reading group presentation Validation of de novo designed water-soluble and transmembrane proteins by in silico folding and melting - comparison of AlphaFold2 vs ESMFold How does over-squashing affect the power of GNNs? feat. Francesco Di Giovanni, Michael Bronstein, and Petar Veličković A Fractional Graph Laplacian Approach to Oversmoothing feat. Gitta Kutyniok