1/3 Twitter graph ML full house at #ICLR2023 : 📜Poster arxiv.org/abs/2210.00513 🔦Spotlight arxiv.org/abs/2210.01542 top 25% 👄Oral arxiv.org/abs/2209.15486 top 5% spanning my recent interests in continuous GNNs, hyperbolic geometry (applied to RL this time) & link prediction

2/3 The culmination and sadly the final act for the team, of which being a part was the highlight of my career. Our recent success is the product of 4y of hard work w/ every submission rejected for the first 18m (those early works are now our most cited.)

This LoRa WAN thing (FreakWAN, as it is done with the FreakNet folks) is going to be a "total project". From the driver to the WAN relay logic, packet format, and, of course, the case of the device itself. It's amazing to create something that looks like a product, from scratch.

Due to the very high number of submissions for our #iclr2023 workshop on Physics for ML we are now in need of extra reviewers. Please message me / the other organisers if willing to review a couple of 4 page papers. You will have out eternal gratitude ❤️.

If platforms shouldn't optimize just for engagement, what should they optimize for? We designed an experiment to test selecting Feed content for long term user value, a collaboration between an international group of researchers and Meta. 1/3 wired.com/story/platform…

Welcome to the LoRa thread. Here I'll talk about LoRa, a modulation used in RF communications that is a game changer for certain applications, and about my work on a LoRa based WAN protocol and implementation: my open source project called FreakWAN.

🎉 We are organizing #EvalRS2023 on the well-rounded evaluation of RecSys at #KDD, covering fairness, bias, robustness, and trustworthiness of #RecSys. We will be accepting papers and also having a hackathon session with awards and prizes! Read more at: reclist.io/kdd2023-cup/

How do you know your #recsys works as expected? After the success of #EvalRS22, we are back at SIGKDD 2025! With prizes for papers, students and projects, #EvalRS is a workshop with a huge social component: come for the papers, stay for the pizza! CFP: reclist.io/kdd2023-cup/

3 May 2023: RIP #fravia gopher.floodgap.com/gopher/gw?a=go…

#recsys, 🌴 and 🍕 - how can you say no? #evalRS is back at SIGKDD 2025 with a new format, half workshop half hackathon! We have prize for students, best papers and cool projects: CFP is out - stay tuned through our website! reclist.io/kdd2023-cup/

EvalRS is brought to you with love by an exceptional team: submit your work, compete for the prize! Claudio Pomo Jacopo Tagliabue Ciro Greco Patrick John Federico Bianchi Gabriel Moreira Fahd Husain Davide Eynard .

⏰Still 9 days to submit to #EvalRS2023 on the well-rounded evaluation of #RecSys at #KDD. Covering fairness, bias, robustness, and trustworthiness of #RecSys. Workshop + hackathon! reclist.io/kdd2023-cup/

My PhD Thesis is finally online. I hope it will provide some new perspectives for anyone interested in geometry, topology, deep learning and graph neural networks. repository.cam.ac.uk/items/06b0b8e5…

Check out our latest work at #ACL2023 ! Toronto might be cold, but our accelerated decoding will heat you up🔥

totally agree

Very glad to give a talk tomorrow at 11 am UK time with great speakers alongside! I will talk about a novel approach to study expressive power of message-passing through its ability to mix features of nodes -- this can be used to characterize/measure over-squashing :-)

Taming randomness in ML models with hypothesis testing and marimo blog.mozilla.ai/taming-randomn…

This blog post by Davide Eynard from mozilla.ai, with input from vicki 🦋, explains the basics of hypothesis testing. It's powered by a marimo notebook that runs entirely in the browser — marimo's interactive elements and Pyodide support make it well-suited to education 💯