GraphML News (June 17th) -- Distributional Graphormer

It seems researchers took a break after NeurIPS deadlines (or braced themselves with the 6-paper reviewing batches) and there hasn’t been that much news lately.

Microsoft Research announced Distributional Graphormer, a massive generative model based on Graphormer suitable for many AI 4 Science tasks such as protein ligand binding, conformation transition pathway prediction, and even conditional crystal lattice generation (eg, generate a structure with a given band gap). Quoting the authors, “DiG attempts to predict the complicated equilibrium distribution of a given system by gradually transforming a simple distribution (e.g., a standard Gaussian) through the simulation of a predicted diffusion process that leads towards the equilibrium distribution.” The accompanying 80-pager preprint is a nice weekend reading 😉

Apart from that, the Learning on Graphs meetup took place in Paris with exciting keynotes, and Michael Bronstein received a prestigious UKRI Turing AI Fellowship (only two were given this year) to work on Graph ML algorithms inspired by physical systems.

More new papers:

Topological Singularity Detection At Multiple Scales (ICML’23) by Julius von Rohrscheidt and Bastian Rieck. Check out a nice Twitter thread by Bastian for a visual explanation.

Generating Novel, Designable, and Diverse Protein Structures by Equivariantly Diffusing Oriented Residue Clouds (ICML’23) by Yeqing Lin, Mohammed AlQuraishi. Genie is 10x smaller than RFDiffusion but gets quite close in terms of generative performance! Have a look at the thread by Mohammed with fancy generated gifs.

Rigid Body Flows for Sampling Molecular Crystal Structures feat. Pim de Haan and Frank Noé

Enabling tabular deep learning when d≫n with an auxiliary knowledge graph feat. Hongyu Ren and Jure Leskovec