Neuro-Symbolic Learning for Relational Databases
Public support
Provider
Czech Science Foundation
Programme
Standard projects
Call for proposals
SGA0202600001
Main participants
České vysoké učení technické v Praze / Fakulta elektrotechnická
Contest type
VS - Public tender
Contract ID
26-22501S
Alternative language
Project name in Czech
Neuro-Symbolic Learning for Relational Databases
Annotation in Czech
We are seeing tremendous successes of large neural networks, enabled primarily by efficient data-parallel processing of the underlying tensor representations on GPUs. However, despite the recent breakthroughs, these models are still fundamentally limited in many aspects considered elementary to AI systems. Particularly, in this proposal, we address the contemporary problem of deep learning with relational and symbolic representations that are omnipresent in the interlinked structures of real-world data yet do not succumb to the pre-canned, fixed-size tensor forms. To surpass this limitation, we propose a principled integration of deep learning with the highly expressive and interpretable formalism of relational logic, effectively introducing a complete neuro-symbolic learning framework for relational databases. Methodologically, we propose to build on a well-founded, symmetry-based approach where both parts of the neural-symbolic integration form a proper special case, enabling us to directly improve and generalize state-of-the-art models, such as Graph Neural Networks, and more.
Scientific branches
R&D category
ZV - Basic research
OECD FORD - main branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
OECD FORD - secondary branch
—
OECD FORD - another secondary branch
—
CEP - equivalent branches <br>(according to the <a href="http://www.vyzkum.cz/storage/att/E6EF7938F0E854BAE520AC119FB22E8D/Prevodnik_oboru_Frascati.pdf">converter</a>)
AF - Documentation, librarianship, work with information<br>BC - Theory and management systems<br>BD - Information theory<br>IN - Informatics
Solution timeline
Realization period - beginning
Jan 1, 2026
Realization period - end
Dec 31, 2028
Project status
Z - Beginning multi-year project
Latest support payment
—
Data delivery to CEP
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data delivery code
CEP26-GA0-GA-R
Data delivery date
May 6, 2026
Finance
Total approved costs
8,484 thou. CZK
Public financial support
8,484 thou. CZK
Other public sources
0 thou. CZK
Non public and foreign sources
0 thou. CZK