Workshop on Foundation Models for Topological Data - Challenges and Opportunities #3
Description
Title
Foundation Models for Topological Data - Challenges and Opportunities
Responsible person(s)
Timo Dickscheid [1,2,3] @dickscheid , Christian Schiffer[1,2] @ch-schiffer , Susanne Wenzel[1,2] @SusanneWenzel , Martin Schultz[4]
[1] Helmholtz AI, Forschungszentrum Jülich
[2] Institute or Neuroscience and Medicine (INM-1), Forschungszentrum Jülich
[3] Institute of Computer Science, Heinrich-Heine-University Düsseldorf
[4] Jülich Super Computing Centre, Forschungszentrum Jülich
Format
Workshop
Timeframe
3-4h
Description
Foundation models have started to revolutionise the field of artificial intelligence and with that many scientific and industrial applications. So far, research on these powerful generalist models resolves around models that operate on images or written language, or sometimes both in combination. In comparison, topological data (e.g., attributed graphs) has received relatively little attention with respect to the development of foundation models, despite its central role in many scientific domains, including climate modelling, neuroscience, molecular science, and remote sensing. With this workshop, we will present and discuss applications from different scientific domains which rely on analysing topological data, and aim to identify common challenges and potential solutions towards developing foundation models for topological data.
Planned format
- 6 speaker á 15 min talks, plus 10 min Q&A
- 30 min open discussion
Requirements
- Seminar room with A/V equipment
- min/max number of attendees: 15-40
Call for contributions
We invited contributions on these topics for 15 minute talks, plus 10 minutes discussion.
Please send a short abstract (not more than 500 words) by May 1st to s.wenzel@fz-juelich.de
[pdf]