GraphGPS (your fav graph transformer) has made a great journey to a proper foundation model, props to Dominique Beaini for driving it all along!

Thrilled to release 🌟STaRK 🌟 - A large-scale LLM retrieval benchmark on semi-structured knowledge bases.

While LLMs excel at reasoning and semantic retrieval, they struggle with more complex tasks. Especially when real-world user queries require a combination of unstructured…

We started releasing the first chapters of our Geometric Deep Learning book and the accompanying slides from the corresponding Oxford and Cambridge courses.

🧵1/6 We're so excited to announce the inaugural machine learning for drug discovery summer school!

🏫 What: Lectures from Yoshua Bengio, Anne Carpenter, PhD, Pratyush Tiwary, Bharath Ramsundar, and more.

📍Where: MilaQuebec

📅 When: June 12th - 21st

Learn more here: portal.ml4dd.com

See what arrived 🤩🚀
(Equiadapt: github.com/arnab39/equiad…)

p.s. You 'may' find me in this at #ICLR 2024 in Vienna. 😅

p.p.s: Inspiration? Michael Galkin obviously.

If you are (or you know) a young researcher interested in doing a post-doc in Chile, mixing probability+graphs+deep learning, please contact me! Please spread this for visibility! (adding some images taken in the last 3 months for motivation)

Our review on diffusion models for protein structures and docking is out Hannes Stärk Gabriele Corso Bowen Jing Regina Barzilay Tommi Jaakkola. This summarize the advancements up to 2023. There have been lots of exciting new works since!
wires.onlinelibrary.wiley.com/doi/10.1002/wc…

Attending to Graph Transformers

Luis Müller, Mikhail Galkin, Christopher Morris, Ladislav Rampášek.

Action editor: Fredrik Johansson.

openreview.net/forum?id=HhbqH…

#graph s #graph #molecular

Happy to announce that our paper “Attending to Graph Transformers” has been accepted at TMLR. We added lots of new and exciting graph transformer works + new experimental results. Check it out:
📝: arxiv.org/abs/2302.04181
💻: github.com/luis-mueller/p…
🎙️: youtu.be/BuNXQIzLBWc?si…

Thrilled to launch EquiAdapt! 🚀

A library for equivariant adaptation of neural networks, including SAM by AI at Meta, making them robust to transformations without losing efficiency: github.com/arnab39/equiad…

w/ Arnab Danielle Benesch Oumar Kaba Jikael Gagnon

🧵

In a new post with Luca Naef VantAI we ask what is needed for ML to succeed in biological problems and argue that it is necessary to move beyond 'white-box data'
michael-bronstein.medium.com/the-road-to-bi…

w inputs from Nathan Benaich Dominique Beaini @befcorr Georg Winter Patrick Schwab Gevorg Grigoryan

𝑪𝒉𝒂𝒕 𝒘𝒊𝒕𝒉 𝒀𝒐𝒖𝒓 𝑮𝒓𝒂𝒑𝒉 🗣️

G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering

ArXiv: arxiv.org/abs/2402.07630
GitHub: github.com/XiaoxinHe/G-Re…
BlogPost: medium.com/@xxhe/graph-re…

Movere a diporto
Con voi, Dottor ⁦Michael Galkin⁩
È onorevole e saggio;
Sediam sovra quel sasso.
Osserva come
Fulgoreggian a vespro
Le capanne.

⁦Michael Galkin⁩ the meme king presenting ULTRA

A GNN coauthors horse ride ⁦İsmail İlkan Ceylan⁩ ⁦Haggai Maron⁩ ⁦Michael Galkin⁩ Andreaa Deac

Learning on Graphs and Geometry, LoGG, is a weekly reading group hosted and organized by Hannes Stärk.

Topics covered: all things graph learning.

Recent speakers: Chieh-Hsin (Jesse) Lai, Michael Galkin, Joey Bose

portal.valencelabs.com/logg

My weekend exercise in porting Neural Bellman Ford nets to MLX and MLX-graphs that runs natively on Apple GPUs: github.com/migalkin/NBFNe…

The MLX ecosystem for Apple Silicon grows very quickly - thanks Tristan Bilot and Awni Hannun for all the help :)

So excited to host Sriraam Natarajan, Mahashweta Das from Visa, Clara Stegehuis, Michael Galkin, Serina Chang, Jiliang Tang, and Karthik Subbian from Amazon for 4th GCLR workshop @AAAI2024. If you are attending AAAI 2024, join us in room 204. Full schedule: sites.google.com/view/gclr2024/…

Unveiling the next chapter in our quest towards the elusive theory of *all* neural networks: Categorical Deep Learning! 🐈🤖

categoricaldeeplearning.com

See thread 🪡 for a bucket list 🪣 of concepts our framework can handle!

w/ Bruno Gavranović P. Lessard Andrew Dudzik Tamara von Glehn joao - mostly away

My brilliant colleague Nikolay Malkin (malkin1729.github.io) is looking for PhD students (fully funded) in for his new lab in Edinburgh, ideally Sept24-Jan25 start! Topics: Bayesian ML (incl. probabilistic reasoning in language), Generative AI, NLP, and neurosymbolic AI.