GraphML News (April 13th) - MoML’24, ICML workshops, ICLR blogposts

🏆 Big news: Avi Wigderson received the Turing Award Prize 2024 for his contributions to randomness in computation along with other works in complexity theory, cryptography, and graph theory. Particularly in graph theory, Avi is well-known for studying expander graphs which recently became quite popular in Graph ML, eg, with Expander Graph Propagation and Exphormer as a sparse attention mechanism in graph transformers. Read more about Avi in this Quanta article.

🧬 Valence Labs and Mila announced the Molecular ML Conference 2024 (MoML) (June 19th) as the key part of the larger 2-week program on structural biology and geometric DL including the Drug Discovery Summer School (June 12-18) and Hackathon (June 20-21). All events will take place in Montreal (and June is the best time to be in Montreal). MoML will feature talks by Dominique Beaini (Valence), Jian Tang (Mila), Christine Allen (U of Toronto), and Max Jaderberg (Isomorphic Labs). The summer school will feature talks by Michael Bronstein, Mario Geiger, Yoshua Bengio, Connor Coley, Charlotte Bunne, and other prominent researchers. A perfect event for ML folks to learn bio, and for biologists to learn SOTA ML methods.

🎤 ICML’24 published a list of accepted workshops: you might be interested in:

- Geometry-grounded Representation Learning and Generative Modeling (GRaM)
- Structured Probabilistic Inference and Generative Modeling
- AI for Science: Scaling in AI for Scientific Discovery
- ML for Life and Material Science: From Theory to Industry Applications

Besides, ICLR published the blog posts accepted to the Blog Post track (a hidden treasure of ICLR) - check out the posts on deriving diffusion models, flow matching, equilibrium models for algorithmic reasoning, and even on computing Hessian-vector products.

📚 Weekend reading:

Simplicial Representation Learning with Neural k-Forms (ICLR 2024) by Kelly Maggs, Celia Hacker, Bastian Rieck - an alternative to message passing using neural k-forms and simplicial complexes

Benchmarking ChatGPT on Algorithmic Reasoning by Sean McLeish, Avi Schwarzschild, Tom Goldstein - turns out that ChatGPT with code interpreter can beat many GNNs on the CLRS benchmark when posing questions and data in natural language (who knew that quickselect, unsolvable by GNNs, could be almost perfectly solved by an LLM?). To be fair, the paper generated quite active discussions on Twitter as to the OOD generalization aspect of CLRS and the fact that LLMs saw all those algorithms many times during pre-training.

Empowering Biomedical Discovery with AI Agents by Shanghua Gao feat. Marinka Zitnik - a survey on advances of AI agents in biomedical discovery and open challenges