Post #757

GraphML News A new blog post Graph Neural Networks for Molecular Dynamics Simulations by Sina Stocker and Johannes Gasteiger covering the basics of molecular dynamics with GemNet and code examples. Teaching old labels new tricks in heterogeneous graphs - a new post by Google Research introducing Knowledge Transfer Networks (NeurIPS’22) - a method for zero-shot transfer on heterogeneous graphs with extreme label scarcity. TigerGraph incorporated NodePiece, a compositional tokenization approach for scalable and inductive graph learning, into a new release - as the author of NodePiece, I am very excited to see academic efforts adopted in industrial DBs! Btw, NodePiece-based approaches have been taking the whole top-10 in OGB WikiKG 2 link prediction benchmark for almost two years now. All talk recordings of the IPAM UCLA workshop on Deep Learning and Combinatorial Optimization are now available! Featuring researchers such as Stefanie Jegelka, Petar Veličković, Xavier Bresson, Kyle Cranmer, and many more. Weekend reading: Complexity of Many-Body Interactions in Transition Metals via Machine-Learned Force Fields from the TM23 Data Set - a new TM23 dataset for molecular dynamics modeling transition metals. Reducing SO(3) Convolutions to SO(2) for Efficient Equivariant GNNs - a neat math trick to reduce computational complexity of equivariant GNNs