Bridging max graph neural networks and datalog with negation
We consider a general class of data transformations based on Graph Neural Networks (GNNs), which can be used for a wide variety of tasks. An important question in this setting is characterising the expressive power of these transformations in terms of a suitable logic-based language. From a practica...
Main Authors: | Tena Cucala, D, Cuenca Grau, B |
---|---|
格式: | Conference item |
语言: | English |
出版: |
IJCAI Organization
2024
|
相似书籍
-
On the correspondence between monotonic max-sum GNNs and datalog
由: Tena Cucala, D, et al.
出版: (2023) -
On the correspondence between monotonic max-sum GNNs and Datalog
由: Tena Cucala, D, et al.
出版: (2023) -
Stratified negation in datalog with metric temporal operators
由: Tena Cucala, D, et al.
出版: (2021) -
DatalogMTL with negation under stable models semantics
由: Wałęga, PA, et al.
出版: (2021) -
The stable model semantics of datalog with metric temporal operators
由: Walega, P, et al.
出版: (2023)