Post #755

Temporal Graph Learning RG, Clifford Networks, Forward-Forward GNNs Temporal Graph Learning reading group - a new reading group by McGill and NEC Labs researchers happening every Thursday 11-12 Eastern Time! Jure Leskovec (Stanford) gave a talk “Towards Universal Cell Embeddings” at the Broad Institute (slides are available) covering the most recent research on single cell analysis with GNNs including MARS for novel cell types, SATURN for joint cell-protein representations, STELLAR for cancer tissue annotation, and GEARS for predicting effects of multi-gene perturbations New papers you might want to have a look at: Geometric Clifford Algebra Networks David Ruhe, Jayesh K. Gupta, Steven de Keninck, Max Welling, and Johannes Brandstetter MSR recently dropped a hefty 50-pager on Clifford Algebras for PDEs, here is the adaptation of Clifford layers for GNNs with applications in object dynamics and fluid mechanics! Check the Twitter thread by David Ruhe for cool visual examples. Graph Neural Networks Go Forward-Forward Daniele Paliotta, Mathieu Alain, Bálint Máté, François Fleuret At the recent NeurIPS’22, Geoff Hinton presented an idea of forward-forward networks without backprop. Instead of building a computation graph for the backward pass, you’d encode the label together with an input data point and ask the trainable layer to distinguish positive label from a negative sample. Here, the authors expand the idea to GNNs and probe forward-forward on graph classification tasks. Interestingly, the results are not that bad - in some cases, FF-GNNs even outperform their backprop counterparts. DiffDock, a diffusion model for protein-ligand docking, has been updated to include new results on blind docking with ESMFold - the model now drastically outperforms industrial tools on RMSD docking accuracy within 2 Angstrom, check the full thread by Gabriele Corso