On the correspondence between monotonic max-sum GNNs and Datalog
Although there has been significant interest in applying machine learning techniques to structured data, the expressivity (i.e., a description of what can be learned) of such techniques is still poorly understood. In this paper, we study data transformations based on graph neural networks (GNNs). Fi...
Main Authors: | Tena Cucala, D, Cuenca Grau, B, Motik, B, Kostylev, EV |
---|---|
Format: | Conference item |
Language: | English |
Published: |
IJCAI Organization
2023
|
Similar Items
-
On the correspondence between monotonic max-sum GNNs and datalog
by: Tena Cucala, D, et al.
Published: (2023) -
Bridging max graph neural networks and datalog with negation
by: Tena Cucala, D, et al.
Published: (2024) -
DatalogMTL with negation under stable models semantics
by: Wałęga, PA, et al.
Published: (2021) -
Stratified negation in datalog with metric temporal operators
by: Tena Cucala, D, et al.
Published: (2021) -
The stable model semantics of datalog with metric temporal operators
by: Walega, P, et al.
Published: (2023)