Galkin

What’s New in Graph ML?A new milestone in graph data managementWe introduce the concept of Neural Graph Databases as the next step in the evolution of graph databases. Tailored for large incomplete graphs and on-the-fly inference of missing edges using graph representation learning, neural reasoning maintains high expressiveness and supports complex logical queries similar to standard graph query languages.Image by Authors, assisted by Stable Diffusion.Neural Graph Databases: What and Why?The blueprint of NGDBsNeural…

STATE OF THE ART DIGESTHot trends and major advancements2022 comes to an end and it is about time to sit down and reflect upon the achievements made in Graph ML as well as to hypothesize about possible breakthroughs in 2023. Tune in 🎄☕Background image generated by DALL-E 2, text added by Author.The article is written together with Hongyu Ren (Stanford University), Zhaocheng Zhu (Mila & University of Montreal). We thank Christopher Morris and Johannes Brandstetter for the feedback and helping with the Theory and PDE…

What’s new in Graph ML?Is Denoising Diffusion all you need?The breakthrough in Denoising Diffusion Probabilistic Models (DDPM) happened about 2 years ago. Since then, we observe dramatic improvements in generation tasks: GLIDE, DALL-E 2, Imagen, Stable Diffusion for images, Diffusion-LM in language modeling, diffusion for video sequences, and even diffusion for reinforcement learning.Diffusion might be the biggest trend in GraphML in 2022 — particularly when applied to drug discovery, molecules and conformer generation,…

What’s New in GraphML?Recent advancements and hot trends, July 2022 editionInternational Conference on Machine Learning (ICML) is one of the premier venues where researchers publish their best work. ICML 2022 was packed with hundreds of papers and numerous workshops dedicated to graphs. We share the overview of the hottest research areas 🔥 in Graph ML.Denoising diffusion probabilistic models (DDPMs) are taking over the field of Deep Learning in 2022 in pretty much all domains with stunning generation quality and better…

Recent Advances in Graph MLRecipes for cooking the best graph transformersIn 2021, graph transformers (GT) won recent molecular property prediction challenges thanks to alleviating many issues pertaining to vanilla message passing GNNs. Here, we try to organize numerous freshly developed GT models into a single GraphGPS framework to enable general, powerful, and scalable graph transformers with linear complexity for all types of Graph ML tasks. Turns out, just a well-tuned GT is enough to show SOTA results on many…