New paper accepted at NeurIPS 2024! On the Expressivity and Sample Complexity of Node-Individualized Graph Neural Networks 📜Paper: openreview.net/pdf?id=8APPypS… 1. Message-passing GNNs are limited by the expressive power of the 1-Weisfeiler-Leman (color refinement) test for graph

Starting in a few minutes 🥳

We’re closing out the Learning on Graphs Conference 2025 meetup in Aachen now with a panel on the relationship between graph learning and computer vision with fantastic panelists 🥳

🌟 GLOW is coming back in December with amazing speakers: Emily Jin and Josh Southern! 🗓️ Dec 18th @ 17 CET on Zoom, don't miss that! 🌐 Find more here: sites.google.com/view/graph-lea…

Join this year's last edition of Graph Learning on Wednesdays (GLOW) tomorrow at 5pm CET!

🌟 GLOW 2025 kicks off with a super session in January! 🎙️ Hear from our amazing speakers Clayton Sanford and Derek Lim. 🗓️ Jan 15th, 17 CET on Zoom. 🌐 Details & sign-up: sites.google.com/view/graph-lea…

Tune in to GLOW next week for my talk on metanetworks!

Dear Network, Jesse Read and I would like to advertise the attached PhD position (start date: September 2025). We would like to work with you in the intersection of Graph Neural Networks, Reinforcement Learning, and Graph Signal Processing. We look forward to hearing from you!

GLOW is starting in 30 minutes! Super excited about the talks today: First Transformer reasoning and then NNs that take other NNs as input 🌟 See you there!!

GLOW is back 𝐭𝐡𝐢𝐬 Wednesday, 🗓️ Februrary 19th, 5pm CET 🌟 Before our returning to our regular format in March, we’re hosting an open discussion on where Graph Learning is headed and where early-career researchers can make the most impact. [1/3]

* Graph Learning Will Lose Relevance Due To Poor Benchmarks * Maya Bechler-Speicher, Ben Finkelshtein, Fabrizio Frasca, Luis Muller, et al. Inc. Michael Bronstein Bryan Perozzi Michael Galkin Christopher Morris Wow we should be discussing / acting on this!

GLOW is returning on 𝗠𝗮𝗿𝗰𝗵 𝟮𝟲𝘁𝗵, 𝟱𝗽𝗺 𝗖𝗘𝗧 with a special guest: Petar Veličković 🌟 He will lecture on LLMs as GNNs – a topic which received quite some attention at our last session. Specifically, we will learn how Graph ML tools can help understand LLM generalisation👓

I am very excited for this 🌟 LLMs meet GL has received a lot of attention at our discussion session last month. And in particular, we wondered how GL can contribute to LLM research. Here’s a chance to find out:

📣 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

Check out this blogpost from Fabrizio Frasca @ ICML 2025 (Vancouver) and the GLOW reading group on the future of graph learning! I’ve also contributed and my main take is - its actually working and its an exciting moment to work on applications!

Nice read! Also, have a look at our two ICML position papers: arxiv.org/abs/2502.14546 (Practice) and arxiv.org/abs/2402.02287 (Theory).

📢 New paper: Distributed computing 🤝 agents in AgentsNet! AgentsNet transforms classical distributed computing problems into a benchmark for evaluating how LLM agents can coordinate when organized in a network Led by Florian Grötschla, Luis Müller, Jan Tönshoff w/ Bryan Perozzi 🧵1/9

I tracked the percentage of people who came by our "Position: Graph Learning Will Lose Relevance Due to Poor Benchmarks" poster at ICML 2025 and agreed with the message - 100%! 😄 A recurring question was: But what should we do? Is the field doomed? Definitely not! I see this