Jacob Bamberger
@jacobbamberger
Followers
228
Following
489
Media
3
Statuses
74
Looking for geometry where it shouldn’t be. PhD student @CompSciOxford. Interested in Geometric Deep Learning
Joined June 2020
🚨 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
2
17
50
RT @leRoux_Scott: Interested in Long-Range Interaractions ? Come speak with us now (4:30pm-7pm) at our poster E-2802 @ #ICML2025 . @benpgut….
0
9
0
RT @AlexanderTong7: Come check out SBG happening now! W-115 11-1:30 with.@charliebtan .@bose_joey .Chen Lin.@leonklein26 .@mmbronstein http….
0
17
0
RT @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. PD….
0
2
0
RT @LogConference: We’re thrilled to share that the first in-person LoG conference is officially happening December 10–12, 2025 at Arizona….
logconference.org
Learning on Graphs Conference
0
26
0
RT @jacobbamberger: 🚨 ICML 2025 Paper 🚨. "On Measuring Long-Range Interactions in Graph Neural Networks". We formalize the long-range probl….
0
17
0
@benpgutteridge @leRoux_Scott @mmbronstein @epomqo Presenting at poster session 4 east. 📅Wednesday, July 16th.🕓4:30-7:00 PM.📈#E-2802.
0
1
4
Read more here:.📄paper: 💻 code: 🙌With @benpgutteridge @leRoux_Scott @mmbronstein @epomqo. #ICML2025 #GNN #AI.
github.com
Contribute to BenGutteridge/range-measure development by creating an account on GitHub.
1
1
9
🔑 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.
1
0
2
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.
1
0
2
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.
2
0
2
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.
1
0
2
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.
1
0
3
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.
1
0
4
"Long-range tasks" are a central yet vague challenge in graph learning. What makes a task long-range? How can we tell if a model actually captures long-range interactions?.
1
0
2
RT @hxyscott: 🚨 Excited to announce that "How Expressive are Knowledge Graph Foundation Models?" is coming to ICML 2025! 🎉. 📅 Wednesday, Ju….
0
18
0
RT @neur_reps: 📢 Call for Papers: NeurReps 2025 ‼️‼️‼️. 🧠 Submit your research on symmetry, geometry, and topology in artificial and biolog….
neurreps.org
Call for Papers
0
38
0
RT @k_neklyudov: (1/n) Sampling from the Boltzmann density better than Molecular Dynamics (MD)? It is possible with PITA 🫓 Progressive Infe….
0
55
0
RT @AGosztolai: 🚀🚀Thrilled to announce that my lab has secured generous funding of 1.6m EUR from the Vienna Science and Technology Fund (ht….
wwtf.at
Vienna Research Groups for Young Investigators
0
3
0
RT @haririAli95: 📢ChebNet is back—with long-range abilities on graphs !🎉. We revive ChebNet for long-range tasks, uncover instability in po….
0
7
0