Petar Veličković (@PetarV

Petar Veličković

3,291 posts

Petar Veličković

@PetarV_93

Senior Staff Research Scientist @GoogleDeepMind | Affiliated Lecturer @Cambridge_Uni | Assoc @clarehall_cam | GDL Scholar @ELLISforEurope. Monoids. 🇷🇸🇲🇪🇧🇦

London 🇬🇧

Joined January 2013

Pinned
Petar Veličković
@PetarV_93
Jul 31, 2022
These days, I receive a lot of email 📬 and realise my communication could be significantly more effective. Please see petar-v.com/contact.html for optimal ways to reach out 📨, and FAQ answers❓(including pointers to materials on GNNs / GDL, and research / internship advice!).
Petar Veličković
@PetarV_93
Sep 17, 2020
As requested , here are a few non-exhaustive resources I'd recommend for getting started with Graph Neural Nets (GNNs), depending on what flavour of learning suits you best. Covering blogs, talks, deep-dives, feeds, data, repositories, books and university courses! A thread 👇
Petar Veličković
@PetarV_93
Aug 3, 2025
in chronological order:
Anthony Bonato
@Anthony_Bonato
Jul 27, 2025
What four math books had a big influence on your mathematical thinking? I'll start:
135K
Petar Veličković
@PetarV_93
Apr 28, 2021
Proud to share our 150-page "proto-book" with @mmbronstein @joanbruna @TacoCohen on geometric DL! Through the lens of symmetries and invariances, we attempt to distill "all you need to build the architectures that are all you need". geometricdeeplearning.com More info below! 🧵
Petar Veličković
@PetarV_93
Aug 8, 2021
Looking for material to dive into geometric deep learning? As part of the @AIMS_Next #AMMI2021, we (@mmbronstein @joanbruna @TacoCohen) have delivered a course on GDL, which closely follows our proto-book. We make all materials publicly available! geometricdeeplearning.com/lectures/
Petar Veličković
@PetarV_93
Feb 22, 2021
The recording of my talk on Theoretical Foundations of Graph Neural Networks is now live (+slides in desc.)! 🕸️ Join me as I derive GNNs from first principles, motivate their use in the sciences, and explain how they emerged along several research lines. youtube.com/watch?v=uF53xs…
Petar Veličković
@PetarV_93
May 14, 2025
2018 ---> 2025
54K
Petar Veličković
@PetarV_93
Jul 27, 2022
📢 New & improved material to dive into geometric deep learning! 💠🕸️ We (@mmbronstein @joanbruna @TacoCohen) delivered our Master's course on GDL @AIMS_Next once again & we make all materials publicly available! geometricdeeplearning.com/lectures/ See thread 🧵 for gems 💎 & dragons 🐉!
Petar Veličković
@PetarV_93
Oct 7, 2020
I make all the graphics in my papers (e.g. the one below) using TikZ. I'm pathologically bad at drawing, so programming my own figures is basically the only way to stay sane. I open-source all of my figures' codes here: github.com/PetarV-/TikZ Feel free to re-use (w/ credit :) )
Petar Veličković
@PetarV_93
Dec 5, 2024
Our team is hiring Student Researchers @GoogleDeepMind for '25! 🧑‍🔬 Interested in understanding reasoning capabilities from first principles? 🧑‍🎓 Currently studying for a BS/MS/PhD? 🧑‍💻 Have solid engineering and research skills? 🌟 We want to hear from you! Details in thread.
110K
Petar Veličković
@PetarV_93
Oct 18, 2021
Promoted to Staff Research Scientist @DeepMind! 🎉 It's been such an exciting year. Algorithmic reasoning has made a dent on meaningful problems, and our work is still ramping up, with many updates planned, even in 2021! 😊 Thank-you to all who supported me in this journey! 🙌
Petar Veličković
@PetarV_93
Dec 1, 2021
Our work has been published in @Nature!! (G)NNs can successfully guide the intuition of mathematicians & yield top-tier results -- in both representation theory & knot theory. dpmd.ai/nature-maths arxiv.org/abs/2111.15161 arxiv.org/abs/2111.15323 See my 🧵 for more insight...
Petar Veličković
@PetarV_93
Oct 28, 2024
Promoted to Senior Staff Research Scientist @GoogleDeepMind 🚀 Energised to push even stronger on exciting foundational research, while also showing off new applied work (soon 👀)! Now more than ever, this would not have been possible without all who supported me. Thank you ❤️
39K
Petar Veličković
@PetarV_93
Jan 20, 2023
Everything is connected! 🕸️🌐 When I talk about GNNs, their success stories, and importantly, how they relate to other neural networks... I find myself often repeating exactly the same words. Here's a paper summarising those words. Hope you like it! 😊
arxiv.org
Everything is Connected: Graph Neural Networks
In many ways, graphs are the main modality of data we receive from nature. This is due to the fact that most of the patterns we see, both in natural and artificial systems, are elegantly...
86K