My first paper with my first PhD student @PedroCVieira0 just landed on arXiv!
“Do Deep Ensembles Actually Capture Uncertainty in Graph Neural Networks?”
Spoiler alert: the answer is largely no—at least, not much more than a single model does. 🧵👇
📄 https://t.co/13rhr70KDH
🔹 Convexity?
Message passing GNNs find different weights but learn remarkably similar functions—even where they fail. We hypothesize the architecture induces function-space convexity, making them behave like linear models despite their depth. Formalizing this is an open problem.
Happy to share a major milestone: after years of development, we are officially launching Version 1.0 of the GeometricKernels library!
To top it off, our accompanying paper has just been published in JMLR (MLOSS)! 🎉
https://t.co/orSv60ydUX
@N0ne_Official We always welcome PRs! There's a few spaces which are still not implemented so if you're interested in doing something like this, just email me and we can discuss 🙂
Bonus: a concrete success story. In the traffic prediction benchmark below, a Geometric GP (powered by GeometricKernels) significantly outperforms GNN Ensembles and Bayesian GNNs in both prediction (RMSE) and uncertainty (NLL) quality.
I am hiring a fully-funded #PhD in #ML to work at @EdinburghUni on 𝐠𝐞𝐨𝐦𝐞𝐭𝐫𝐢𝐜 𝐥𝐞𝐚𝐫𝐧𝐢𝐧𝐠 and 𝐮𝐧𝐜𝐞𝐫𝐭𝐚𝐢𝐧𝐭𝐲 𝐪𝐮𝐚𝐧𝐭𝐢𝐟𝐢𝐜𝐚𝐭𝐢𝐨𝐧.
Application deadline: 31 Dec '25. Starts May/Sep '26.
Details in the reply.
Pls RT and share with anyone interested!