GAIN @gain@qoto.org

We are very happy to be starting the joint project GraphPCBS together with Intelligent Embedded Systems | Universität Kassel and CELUS.

Together we will use Graph Neural Networks to automatically optimize the schematic design of printed circuit boards. Until now, the optimization takes a a lot of time even for an experienced engineer, resulting in either high costs or not fully optimized circuits and thus electronic products more vulnerable to failure and a short life-time. In this project we combine forces in the fields of deep learning on graphs and electronic engineering to solve this problem.
If you would like to help us in doing so, we are looking for a new colleague to be part of the project. For more information and on how to apply, please have a look here. https://stellen.uni-kassel.de/jobposting/6e23d72336ffaaa15ebb24a6178c8043b4a613dd0 .

A big thank you to Björn Mamat and ifectis Innovationsförderung for the help in writing the proposal!

Due to the many requests, we have decided to open our workshop for online-participation. If you are interested, go to https://gain-group.de/html/events.html for more information. See you there (:

We are hosting our annual workshop 6-8th of September in Kassel, Germany.
This years topic is 'Explainability and Applicability of Graph Neural Networks'.

Check out our homepage for more infos and registration!
https://gain-group.de/html/events.html

We are looking for student research assistants! If you study at any German university, are skilled in python and interested in graph neural networks, check out the job description here
https://gain-group.de/resources/jobs/Stellenausschreibung_GAIN.pdf
and/or toot/email us for questions or directly send your application.

Silvia won the Best Poster Presentation Award at the 21st Symposium on Intelligent Data Analysis (IDA 2023) in Louvain-la-Neuve! https://ida2023.org/
She presented a poster illustrating her current dissertation status about Stuctural-Dynamic Graph Embeddings and a poster about the recent work under review at Elsevier's Transactions on Neural Networks with the title Weisfeiler-Lehman goes Dynamic: An Analysis of the Expressive Power of Graph Neural Networks for Attributed and Dynamic Graphs. https://arxiv.org/pdf/2210.03990.pdf

Also the paper Power Flow Forecasts at Transmission Grid Nodes Using Graph Neural Networks has been published in the Special Issue Smart Grid and AI of the Open Access Journal Energy and AI. It is a collaborative work with the Fraunhofer IEE Kassel developed by Dominik Beinert and Clara Holzhüter.
https://www.sciencedirect.com/science/article/pii/S2666546823000344?via%3Dihub

We are very happy that our Paper Graph Neural Networks Designed for Different Graph Types: A Survey has been accepted and published by Transactions on Machine Learning Research (TMLR)
https://openreview.net/forum?id=h4BYtZ79uy

Hey everyone, kind of a long silence on our side, but lots of good news!

Are you interested in learning about new advances in the field of Graph Neural Networks?

Then, join our workshop "Hot Topics in Graph Neural Networks" on the 25th of October 2022 from 10 am to 6 pm (CET) .

https://gain-group.de/html/events.html

#jobsearch
GNN=Graph Neural Network (;

We finally uploaded the recorded talks/slides from our kickoff to the homepage:

https://gain-group.de/kickoff.html

If you are interested in graphs, graph neural networks and or their application in neuroscience, the electrical power grid or even quantum gravitation you should have a look!

We are looking for one more PhD student to work on the generation of graphs with GNNs (:

If you are a good programmer, interested in GNNs and not afraid of math, checkout our homepage for more info
https://gain-group.de/openpositions.html

A link to apply can be found there, too. If you are interested in renewable energies as well, even better!