Jacob Bamberger
@jacobbam.bsky.social
ML PhD student at University of Oxford. Interested in Geometric Deep Learning
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.
This measure applies to both node- and graph-level tasks, and across architectures.
July 13, 2025 at 2:30 PM
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.
This measure applies to both node- and graph-level tasks, and across architectures.
🚨 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 👇
"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 👇
July 13, 2025 at 2:30 PM
🚨 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 👇
"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 👇
It’s a wrap! Thank you to everyone that joined LoG-ox, the Oxford local meet up for @logconference.bsky.social!
November 25, 2024 at 10:01 PM
It’s a wrap! Thank you to everyone that joined LoG-ox, the Oxford local meet up for @logconference.bsky.social!