Viacheslav Borovitskiy

Assistant Professor in Machine Learning @EdinburghUni. PhD in Mathematics. Ex @ETH_en.

See

[Viacheslav Borovitskiy @vabor112]

@markvanderwilk @PedroCVieira0 @pedroribeiro_pt Thanks, Mark!

[Viacheslav Borovitskiy @vabor112]

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

[Viacheslav Borovitskiy @vabor112]

💻 Code: https://t.co/tLL1y3NrPn
📄 Preprint: https://t.co/13rhr70KDH

Co-authored w/ @PedroCVieira0 & @pedroribeiro_pt.

#MachineLearning #GraphNeuralNetworks #DeepLearning #UncertaintyQuantification #GeometricDeepLearning

[Viacheslav Borovitskiy @vabor112]

🔹 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.

[Viacheslav Borovitskiy @vabor112]

@N0ne_Official >Geoopt
I believe no.
> Pytorch
Core PyTorch and GPyTorch - no, but the library itself integrates nicely with them.

[Viacheslav Borovitskiy @vabor112]

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

[Viacheslav Borovitskiy @vabor112]

@greghintner Hi! Not sure what you mean. We support meshes if that clarifies it.

[Viacheslav Borovitskiy @vabor112]

@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 🙂

[Viacheslav Borovitskiy @vabor112]

Reproduce it with https://t.co/aOOoJhHS6T

[Viacheslav Borovitskiy @vabor112]

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.

[Viacheslav Borovitskiy @vabor112]

@EdinburghUni Note: I am also recruiting through @ELLISforEurope PhD program (https://t.co/HCru6gfiM3).

[Viacheslav Borovitskiy @vabor112]

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!

[Viacheslav Borovitskiy @vabor112]

Details: https://t.co/87Uz4eOApH.