iiinova — where your digital self keeps evolving

Pascal Welke @pascalwelke.bsky.social · 16/07/2025

Thursday at ICML: WILTing Trees: Interpreting the Distance Between MPNN Embeddings openreview.net/forum?id=lfl... Visit Masahiro at the Thursday afternoon poster session: 4:30 p.m. PDT — 7 p.m. PDT East Exhibition Hall A-B #E-2903

openreview.net

WILTing Trees: Interpreting the Distance Between MPNN Embeddings

We investigate the distance function learned by message passing neural networks (MPNNs) in specific tasks, aiming to capture the _functional_ distance between prediction targets that MPNNs...

100

Pascal Welke @pascalwelke.bsky.social · 20/06/2025

Community Takes on the Future of Graph Learning Check out the outcomes of a very interesting discussion in our GLOW reading group. glowreadinggroup.substack.com/p/community-...

glowreadinggroup.substack.com

Community Takes on the Future of Graph Learning

On drifting goals, fresh frontiers, and a bittersweet lesson we are slowly learning

030

Pascal Welke @pascalwelke.bsky.social · 11/06/2025

Attended my first @netsciconf.bsky.social last week and it was amazing! A highlight was the HONAI satellite that brought together the network science and machine learning communities. ...and who needs NeurIPS mugs if one can have NetSci toilet paper?

010

Reposted by Pascal Welke

Max Thiessen @maxthiessen.bsky.social · 25/05/2025

After a break in April we welcome all of you to the next session of GLOW🌟 next week! Join and interact with our speakers Christian Koke (scale in GNNs) and Yonatan Sverdlov (sparse geometric MPNNs). 🗓️ May 28th, 5pm CEST on Zoom. 🌐 Details & sign-up: sites.google.com/view/graph-learning-on-weds.

056

Pascal Welke @pascalwelke.bsky.social · 22/04/2025

🗓 The date is out: 15/09/2025 Come meet the graph community in Porto @MLG to discuss the latest developments and ideas in the field! 💡We welcome many kinds of papers beyond regular ones such as Work-in-progress papers or Visionary (white) papers! Submit by June 14th mlg-europe.github.io/2025

mlg-europe.github.io

MLG 2025

031

Pascal Welke @pascalwelke.bsky.social · 21/03/2025

Today, I gave a talk on Expressive Graph Representations via Homomorphisms in Subhankar Mishras lab at NISER, India. For all those (all - 50) people who missed it at the LoG Paris meetup, there is now a recording available: www.niser.ac.in/~smishra/eve... Thanks for the invite!

niser.ac.in

010

Reposted by Pascal Welke

Max Thiessen @maxthiessen.bsky.social · 20/03/2025

GLOW is returning on 𝗠𝗮𝗿𝗰𝗵 𝟮𝟲𝘁𝗵, 𝟱𝗽𝗺 𝗖𝗘𝗧 with a special guest: @petar-v.bsky.social 🌟 He will lecture on LLMs as GNNs – a topic which received quite some attention at our last session. Specifically, we will learn how Graph ML tools can help understand LLM generalisation

1127

Reposted by Pascal Welke

Stefan Neumann @neumannstefan.com · 29/01/2025

I am hiring for a Ph.D. student to work in the areas of social network analysis, algorithms and fair machine learning. Please apply and join our highly motivated team. For more information please see the call: neumannstefan.com/hiring/

neumannstefan.com

Call for Doctoral Students in Social Network Analysis, Algorithms and Fair Machine Learning

096

Pascal Welke @pascalwelke.bsky.social · 15/01/2025

In two hours (i.e., 5pm CET), we'll have the first GLOW meeting of the year. Join us for two interesting talks and detailed discussions!

042

Reposted by Pascal Welke

Nicolas Keriven @nicolaskeriven.bsky.social · 09/01/2025

We organise a thematic day on Graph Machine Learning and Graph Neural Networks at IHP in Paris on March 31st. Please consider submitting abstracts! It'll be fun 🤓 Free mandatory registration: gdr-iasis.cnrs.fr/reunions/app...

gdr-iasis.cnrs.fr

Apprentissage et Graphes - GdR IASIS

1218

Reposted by Pascal Welke

Max Thiessen @maxthiessen.bsky.social · 10/01/2025

🌟 GLOW 2025 kicks off with a great session in January! Join and interact with our speakers Clayton Sanford (on transformers for graph algorithms) and Derek Lim (on graph metanetworks). 🗓️ Jan 15th, 5pm CET on Zoom. 🌐 Details & sign-up: sites.google.com/view/graph-learning-on-weds.

021

Reposted by Pascal Welke

Max Thiessen @maxthiessen.bsky.social · 07/01/2025

Ever needed a graph neural network with maximal expressivity on almost all molecules (aka 𝗼𝘂𝘁𝗲𝗿𝗽𝗹𝗮𝗻𝗮𝗿 graphs)? Turns out you only need a simple graph transformation called 𝐶𝐴𝑇! Short talk: youtube.com/watch?v=AW6C... TMLR paper: openreview.net/forum?id=XxbQA

2121

Pascal Welke @pascalwelke.bsky.social · 18/12/2024

Happening right now. Join via zoom: rwth.zoom.us/j/6321681001...

google.com

Redirecting

020

Pascal Welke @pascalwelke.bsky.social · 15/12/2024

Is Expressivity Essential for the Predictive Performance of Graph Neural Networks? Spoiler alert: No. Check out our poster at the Sci4DL workshop, today at 4.30pm, West Meeting Room 205-207 Paper: pwelke.de/publications... Poster: pwelke.de/publications...

TL;DR More expressive GNNs outperform less expressive GNNs not due to expressivity.

Pdf Version of the poster, as well as the paper is available at https://pwelke.de

0100

Pascal Welke @pascalwelke.bsky.social · 13/12/2024

Today at NeurIPS: Weisfeiler and Leman go Loopy: A New Hierarchy for Graph Representational Learning Cycles are important for predictive tasks on chemical molecules. We allow message passing along neighboring paths. Our architecture can subgraph-count cycles and homomorphism-count cactus graphs.

Visual depiction of r-lGIN: During preprocessing, we calculate the path neighborhoods Nr (v) for each node v in the graph G. Paths of varying lengths are processed separately using simple GINs, and their embeddings are pooled to obtain the final graph embedding. The forward complexity scales linearly with the sizes of Nr (v), enabling efficient computation on sparse graphs.

161

Pascal Welke @pascalwelke.bsky.social · 04/12/2024

The @logconference.bsky.social meetup Italy starts today in Siena. I'll certainly be there to enjoy presentations and posters on graph learning. Let's chat! And of course, I'll enjoy beautiful Siena and amazing food. sites.google.com/student.unis...

sites.google.com

LOG24 - Italy meetup

Learning on Graphs is an annual research conference that covers areas broadly related to machine learning on graphs and geometry. Siena will host the 2024 Italy meetup. 🗓️ 4-6 December 2024 📍 Siena,...

030

Pascal Welke @pascalwelke.bsky.social · 03/12/2024

Give yourself an early Christmas present: Visit GLOW and learn about two amazing papers and interact with their authors!

052

Pascal Welke @pascalwelke.bsky.social · 01/12/2024

Had an incredible time at the Learning on Graphs meetup in Paris! Amazing energy, awesome presentations, and lovely posters. I was honored to give a keynote on graph representation learning via homomorphisms and loved the insightful questions and vibrant discussions.

140