🚨 ICML 2025 Paper 🚨 "On Measuring Long-Range Interactions in Graph Neural Networks" We formalize the long-range problem in GNNs: 💡Derive a principled range measure 🔧 Tools to assess models & benchmarks 🔬Critically assess LRGB 🧵 Thread below 👇 #ICML2025

We figured out flow matching over states that change dimension. With "Branching Flows", the model decides how big things must be! This works wherever flow matching works, with discrete, continuous, and manifold states. We think this will unlock some genuinely new capabilities.

Cool news: our extended Riemannian Gaussian VFM paper is out! 🔮 We define and study a variational objective for probability flows 🌀 on manifolds with closed-form geodesics. @FEijkelboom @a_ppln @CongLiu202212 @wellingmax @jwvdm @erikjbekkers 🔥 📜 https://t.co/PE6I6YcoTn

Introducing Generalised Flow Maps 🎉 A stable, few-step generative model on Riemannian manifolds 🪩 📚 Read it at: https://t.co/iCTHedwCxf 💾 Code: https://t.co/MeukcthFN2 @msalbergo @nmboffi @mmbronstein @bose_joey

#AITHYRA, Vienna's new Biomedical AI institute, is hiring Postdocs! Come work with us. Openings in: 🔹 Generative AI 🔹 Multimodal ML 🔹 Virology 🔹 Enzyme Function Apply by Nov 20: https://t.co/8jNpkhdw1x #PostDoc #AI #ML #Vienna #ScienceJobs

🚨 How do attention sinks relate to information flow in LLMs? We show how massive activations create attention sinks and compression valleys, revealing a three-stage theory of information flow in LLMs. 🧵 w/ Enrique* @fedzbar @epomqo @mmbronstein @ylecun @ziv_ravid

Thanks @kwangmoo_yi! Thread coming soon 😁

Time to give ChebNet another life? 🤔🧐 Interesting work! Congrats @haririAli95 @arroyo_alvr 🎉

Interested in Long-Range Interaractions ? Come speak with us now (4:30pm-7pm) at our poster E-2802 @ #ICML2025 @benpgutteridge @jacobbamberger @mmbronstein @epomqo

Come check out SBG happening now! W-115 11-1:30 with @charliebtan @bose_joey Chen Lin @leonklein26 @mmbronstein

5. On Measuring Long-Range Interactions in Graph Neural Networks East Exhibition Hall A-B #E-2802 Wed 16 Jul 4:30 p.m. PDT @jacobbamberger @benpgutteridge @leRoux_Scott @epomqo

We’re thrilled to share that the first in-person LoG conference is officially happening December 10–12, 2025 at Arizona State University https://t.co/Js9FSm6p3N Important Deadlines: Abstract: Aug 22 Submission: Aug 29 Reviews: Sept 3–27 Rebuttal: Oct 1–15 Notifications: Oct 20

🚨 ICML 2025 Paper 🚨 "On Measuring Long-Range Interactions in Graph Neural Networks" We formalize the long-range problem in GNNs: 💡Derive a principled range measure 🔧 Tools to assess models & benchmarks 🔬Critically assess LRGB 🧵 Thread below 👇 #ICML2025

@benpgutteridge @leRoux_Scott @mmbronstein @epomqo Presenting at poster session 4 east. 📅Wednesday, July 16th 🕓4:30-7:00 PM 📈#E-2802

Read more here: 📄paper: https://t.co/yvraKeZfUg 💻 code: https://t.co/eBcDnYrDaR 🙌With @benpgutteridge @leRoux_Scott @mmbronstein @epomqo #ICML2025 #GNN #AI

🔑 Takeaways: ✅ Long-range can be formalized & measured ✅ Reveals new insights into models & datasets 🚀 Time to rethink evaluation: not just accuracy, but how models solve tasks

Why does this matter? "Long-range" is often just a dataset intuition or model label. We offer a measurable way to: 💡Understand models 🧪Test benchmarks 🦮Guide model design 🚀Go beyond performance gaps

We reassess LRGB, the go-to long-range benchmark, by checking if model range correlates with performance—expected for truly long-range tasks. Surprisingly: ❌ Peptides-func: negative correlation, suggests not long-range ✅ VOC: positive correlation, suggests long-range

We validate our framework in three steps: 👷Construct synthetic tasks with analytically-known range 💯Show trained GNNs can approximate the true task range 🔬Use range as a proxy to evaluate real benchmarks

Our measure uses the model's Jacobian (for node tasks) and Hessian (for graph tasks) to quantify input-output influence, works with any distance metric, and supports analysis at all granularities—node, graph, and dataset.

We propose a formal range measure for any graph operator, derived from natural axioms (like locality, additivity, homogeneity) — and show it’s the unique measure satisfying these. This measure applies to both node- and graph-level tasks, and across architectures.