🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Attending Expo day at #ICML2024? Check out our Expo session, "Giving your Graph a Voice: Graph Representations and Large Language Models" today at 1pm CEST (Hall A8) to learn about all the work we've been doing to integrate graph learning with AI!

Also, thanks to Michael Bronstein, Michael Galkin, Christopher Morris and Bryan Perozzi for joining the panel discussion starting around 17.00. We look forward to hearing more about the views on the future challenges and applications of GNNs 🕸

I'm gonna try a live demo training GraphTokens with Gemma - send good vibes for the TPU gods 🙏.

Amazing hot takes on GNNs from Bryan Perozzi Michael Bronstein Christopher Morris Michael Galkin 🔥🌶️ #ICML2024

Congratulations to Bryan Perozzi (Bryan Perozzi) et al. for winning the ACM SIGKDD Test of Time Award for “DeepWalk: Online Learning of Social Representations”, which set the stage for graph neural network research. arxiv.org/abs/1403.6652 #KDD2024 SIGKDD 2025

Be sure to attend today's #NeurIPS2024 EXPO session on Graph Reasoning in Large Language Models at 4pm, where the Google Research Graph Mining team will discuss how to understand and enhance the reasoning capabilities of LLMs. Session details at: neurips.cc/Expo/Conferenc…

See you @ tomorrow's poster session, poster #2300! #NeurIPS2024

How can we best encode structured data into sequential form for LLMs? Join Bryan Perozzi for a live demo today at 12:30PM at the #NeurIPS2024 Google Research booth to learn how Graph Tokens significantly boost an LLM's ability to solve graph reasoning tasks. arxiv.org/pdf/2402.05862

The Google Research blogpost is out! Which classes of graph problems can "thinking" models solve more efficiently than pure transformers? Answer in the paper~ research.google/blog/understan…

Today on the blog, we share a comprehensive evaluation of transformer models’ graph reasoning capabilities, shedding light on their effectiveness across a variety of graph reasoning tasks and introducing a novel representational hierarchy. Learn more →goo.gle/3P7l72k

Got a new blog post up about how researchers at Google have advanced the field of graph learning!

Scaling Large Language Models for Next-Generation Single-Cell Analysis biorxiv.org/content/10.110… #biorxiv_bioinfo

What if LLMs could “read” & “write” biology? 🤔 Introducing C2S‑Scale—a Yale University + Google AI Google DeepMind collab: we scaled LLMs (up to 27 B!) to analyze & generate single‑cell insights by turning transcriptomes into text 🧬➡️📝 🔗 Blog: research.google/blog/teaching-… 🔗 Preprint:

Honored to have Google AI feature our Yale University + Google DeepMind collaboration teaching LLMs the language of biology 🧬➡️📝 research.google/blog/teaching-…

This is a landmark paper I’ve been waiting for-toward creating “virtual cells,” which will revolutionize how we study & interact with biological systems in silico through AI rather than in the wet lab! This should’ve been major news! Congrats to Google AI team & David van Dijk

Fun fact: we actually suggested modeling biological sequences to our advisor as a follow up to DeepWalk in 2013. Happy to finally be scratching this itch 😄

📣 Our spicy ICML 2025 position paper: “Graph Learning Will Lose Relevance Due To Poor Benchmarks”. Graph learning is less trendy in the ML world than it was in 2020-2022. We believe the problem is in poor benchmarks that hold the field back - and suggest ways to fix it! 🧵1/10