iiinova — where your digital self keeps evolving

iiinova is part of the Atmosphere — an open, public network where you own your identity.

Martin Carrasco

@martin.topology.rocks

457 followers 523 following 30 posts

ELLIS PhD @ AIDOS - Interested in Geometrical Deep Learning | Topological Deep Learning | Graphs

Posts Replies Media

Martin Carrasco @martin.topology.rocks · 04/03/2026

We find it does great on non-isomorphic graph distinction by evaluating on BREC icml.cc/virtual/2024... and as an inductive bias on ZINC (compared to other homomorphism and subgraph count methods)

011 1

Martin Carrasco @martin.topology.rocks · 04/03/2026

Not all is lost because we can approximate our true metric by sampling computable graphs (of a nice treewidth) and also homomorphisms!

111 1

Martin Carrasco @martin.topology.rocks · 04/03/2026

Inspired by the 𝘎𝘳𝘰𝘮𝘰𝘷-𝘏𝘢𝘶𝘴𝘴𝘥𝘰𝘳𝘧 distance, we define distortion as the maximum difference of the attributes of a graph 𝗚 and a graph 𝗚' through a homomorphism. We construct a metric from this 𝘥𝘪𝘴𝘵𝘰𝘳𝘵𝘪𝘰𝘯 by taking the homomorphism providing the infimum result and looking at both directions!

111 1

Martin Carrasco @martin.topology.rocks · 25/08/2025

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

000 0

Martin Carrasco @martin.topology.rocks · 26/05/2025

The model relies on positional and structural encodings (PSE) of the combinatorial domain. By decomposing a combinatorial representation into neighborhoods which take the form of a Hasse graph, the PSE of each can be used to discard the topology and learn from the PSE! (4/6)

153 5

Martin Carrasco @martin.topology.rocks · 26/05/2025

🚨Higher-order combinatorial models in TDL are notoriously slow and resource-hungry. Can we do better? Introducing: 🚀 𝐇𝐎𝐏𝐒𝐄: A Scalable Higher-Order Positional and Structural Encoder for Combinatorial Representations 🚀 📝 arXiv: arxiv.org/abs/2505.15405 🧵 (1/6)

1125 12

Martin Carrasco @martin.topology.rocks · 01/05/2025

It came! Excited that I will be attending @logml.bsky.social in London the second week of July, I am happy to connect with fellow colleagues interested in geometry, topology and graphs in ML :) 🛟

061 6