There are less than 5 days left to submit your work to the Deep Learning for Code workshop! Torsten Scholak Gabe Orlanski Disha Shrivastava Arun Raja 🇺🇦 Dzmitry Bahdanau Jonathan Herzig #DL4C #ICLR2022 #iclr2022

🎉🎉Today is the day! 🎉🎉 We are extremely excited to welcome everyone to the Deep Learning For Code Workshop starting now! ICLR: iclr.cc/virtual/2022/w… Site: dl4c.github.io

Very cool paper showing that GNNs work in practical biological applications. It takes several years of effort to produce an experimental validation of computational results

I am excited to announce that our latest work "A Theory of Link Prediction via Relational Weisfeiler-Leman on Knowledge Graphs", together with Miguel Romero, İsmail İlkan Ceylan, and Pablo Barceló, will be presented in #NeurIPS 2023. Arxiv link: arxiv.org/pdf/2302.02209… (1/2)🧵

Harvesting Chemical Understanding with Machine Learning and Quantum Computers #machinelearning #compchem pubs.acs.org/doi/abs/10.102…

"Future Directions in Foundations of Graph Machine Learning" by Haggai Maron ,İsmail İlkan Ceylan, Fabrizio Frasca, Derek Lim, Michael Bronstein et al. Paper: arxiv.org/abs/2402.02287 #graphneuralnetworks

This is the fundamental problem the field of AI for Science aims to solve

OPIG has several papers accepted at the #ICML24 main conference and workshops on the topics of diffusion models for structure-based drug design, antibody design, protein language models and molecular property prediction... (1/7)

OPIGlets are out in force at #AIChem24, organised by our very own Garrett M. Morris DPhil students Lucy Vost, Arun Raja and Ísak Valsson are presenting posters, and Yael is giving a talk about her recent work MolSnapper on Wednesday! Please come and chat to them!

Finally, Arun Raja has explored the effectiveness of quantum chemistry pre-training GNNs for pharmacological property prediction openreview.net/pdf?id=ffSLXl6…

On the Effectiveness of Quantum Chemistry Pre-training for Pharmacological Property Prediction Oxford Protein Informatics Group (OPIG) 1. Quantum chemistry pre-training has shown promise in boosting the accuracy of pharmacological property prediction models. The study focuses on enhancing deep learning

Every AI chemistry talk ever: "We need more data!" never does anyone say "I'm so grateful for the data we have" or "here are 10 more data points." Just complaint after complaint from these chemists