Martin Carrasco

Homomorphism distortion: A metric to distinguish them all and in the latent space bind them For far too long, expressivity of graph neural networks has been measured \emph{only} in terms of combinatorial properties. In this work we stray away from this tradition and provide a principled way ...

All these insights resulted in a 9.5/10 thesis grade (whatever that means), which I hope serves as a hook to give it a read!

📖 On arxiv: arxiv.org/abs/2511.03068

Under mild assumptions, we obtain a metric and we show 𝘤𝘰𝘮𝘱𝘭𝘦𝘵𝘯𝘦𝘴𝘴. However, as all graphs enthusiasts might notice, this implies the GI problem.

That's not the end of the story because we show that we can sample graphs and achieve completeness in expectation :0 !

My thesis project embarks on this question, under the supervision of both @erikjbekkers.bsky.social , @pseudomanifold.topology.rocks and @olgatticus.bsky.social we devise a metric over graphs, 𝘵𝘩𝘳𝘰𝘶𝘨𝘩 the maps that exists between them. It also has a cool name!

𝐇𝐨𝐦𝐨𝐦𝐨𝐫𝐩𝐡𝐢𝐬𝐦 𝐃𝐢𝐬𝐭𝐨𝐫𝐭𝐢𝐨𝐧 (ⒽⒹ)

Two month flew by since the start of the PhD journey with @pseudomanifold.topology.rocks and now the time is right to share how our collaborations officially started, with a question:

How can we measure difference in (attributed) graphs beyond binary isomorphism testing ? 🌀

!!!

It may only be a band-aid, but we have just announced our new "Salon des Refusés" sessions for papers rejected due to space constraints: bsky.app/profile/euri...

Oh come on, a #NeurIPS rejection based on sensible, well-argumented reviews which show an understanding of the paper and its limitations?

HOW AM I SUPPOSED TO COMPLAIN NOW?

"Like all good stories, the tale of EurIPS begins in the kitchen…"

📣📣📣
We are proud to announce our #EurIPS Affinity Events which will take place during the main conference days.
Our Affinity Workshop Chairs have accepted three great proposals from well-renowned organizations

@wimlworkshop.bsky.social
Learning Theory Alliance
@queerinai.com

See you in Copenhagen!

📢 Interested in doing a PhD in generative models 🤖, AI4Science 🧬, Sampling 🧑‍🔬, and beyond? I am hiring PhD students at Imperial College London for the next application cycle.

🔗See the call below:
joeybose.github.io/phd-positions/

✨ And a light expression of interest: forms.gle/FpgTiuatz9ft...

Søren Hauberg (DTU) gives a quick tour of the site of EurIPS 2025: Bella Center, which features its own Metro stop, 13 min. from the airport, 9 min. to the center of town 🚊

The workshops focused on (in chronological order):

- Variational Inference (youtube.com/playlist?lis...)
- Optimal Transport (youtube.com/playlist?lis...)
- Parallel Computing (youtube.com/playlist?lis...), and
- Computational Physics (youtube.com/playlist?lis...).

#EurIPS sure is community-driven!

Across our Calls for Workshops and Affinity Workshops we received a whopping 50+ proposals! Our Workshop and Affinity Workshop Chairs are now busy reviewing and discussing all proposals, and we plan to have the decisions ready mid-September 🤞

We just wrapped up the 5th Summer Geometry Initiative (SGI), bringing 30 Fellows to our cohort of 150+ alumni, who go on to PhD/MS programs, industry jobs, and more. Despite overwhelming success, SGI26 is uncertain thanks to the changing funding landscape. Please help by helping identify sponsors!

Friday afternoon! Finally time to look back at a busy week, and ask oneself — "wait, what did I do, again?"

Bluesky now platform of choice for science community It’s not just you. Survey says: “Twitter sucks now and all the cool kids are moving to Bluesky”…

arstechnica.com/science/2025...

Let's push for the obvious solution: Dear @neuripsconf.bsky.social ! Allow authors to present accepted papers at EurIPS instead of NeurIPS rather than just additionally. Likely, at least 500 papers would move to Copenhagen, problem solved.

First promo photo appearance 🥹

Interested in #topological deep learning (TDL) but not sure where to start? 🍩🤖

Check out #TopoBench, a comprehensive, modular library that benchmarks a wide variety of TDL models across diverse datasets.

Thrilled to see it accepted at DMLR!

Code+Papers:
geometric-intelligence.github.io/TopoBench/

We can’t wait to see what the community builds with TopoBench! Star our repo, read the paper, and bring reproducibility to your TDL research. Contributions and feedback are welcome! #OpenSource #Python #AcademicTwitter

This was a massive team effort!
Developed & led by @levtelyatnikov.bsky.social , @gbg141.bsky.social , Theodore Papamarkou. With major contributions from @Marco Montagna, Mustafa Hajij, Ghada Zamzmi, Michael T. Schaub, @ninamiolane.bsky.social , & @sscardapane.bsky.social , and many others!

GitHub - geometric-intelligence/TopoBench: TopoBench is a Python library designed to standardize benchmarking and accelerate research in Topological Deep Learning TopoBench is a Python library designed to standardize benchmarking and accelerate research in Topological Deep Learning - geometric-intelligence/TopoBench

Delighted to announce TopoBench has been accepted to DMLR! It’s a modular library for Topological Deep Learning, built to provide reproducible, cross-domain benchmarks and accelerate research. GitHub: github.com/geometric-in... #AI #DeepLearning

It is very refreshing seeing the start of a summer school be about Ethics in AI calling out the hype on GenAI as the frontier of human reasoning. Listening to this I am reminded of Feyerabend…
“The only absolute truth is that there are no absolute truths”
#EDS2025

Vapnik-Chervonenkis candy bar

📢 Save the date!
Join us for the next @ellis.eu x UniReps Speaker Series!
📅 27th August – 16:00 CEST
📍https://ethz.zoom.us/j/66426188160
🎙️ Speakers: Keynote by @lelandmcinnes.bsky.social & Flash Talk by Yu (Demi) Qin
🔔 Stay updated by joining our Google group: groups.google.com/u/2/g/ellis-...

In the 20th century, non-Euclidean geometry transformed how we model the world with pen and paper.

Now, it is disrupting how we model the world with machines.

Learn more in our illustrated guide to non-Euclidean ML and AI👇

The world is a beautiful and fragile place that we are allowed to enjoy temporarily and should feel responsible for.

It’s regrettable that we (the ML community) don’t manage to have decentralised conferences across the globe (look at you, @neuripsconf.bsky.social).

Let's be better together!

TGLib: An Open-Source Library for Temporal Graph Analysis We initiate an open-source library for the efficient analysis of temporal graphs. We consider one of the standard models of dynamic networks in which each edge has a discrete timestamp and transition ...

🚀 TGLib is now on PyPI!
Our open-source library for efficient temporal graph analysis is now easy to install (Linux):

pip install temporalgraphlib

📄 Paper: arxiv.org/abs/2209.12587

💻 Code: gitlab.com/tgpublic/tglib

#TGLib #TemporalGraphs #Python #OpenSource #NetworkScience

:0 wow pretty pictures!

Speaking from personal experience, the talks given by @pseudomanifold.topology.rocks are next level!

Definitely a must see by
@unireps.bsky.social !