City Research Online

Abstract

This paper aims to bridge this gap between neuro-symbolic learning (NSL) and
graph neural networks (GNN) approaches and provide a comparative study. We
argue that the natural evolution of NSL leads to GNNs, while the logic
programming foundations of NSL can bring powerful tools to improve the way
information is represented and pre-processed for the GNN. In order to make
this comparison, we propose HetSAGE, a GNN architecture that can efficiently
deal with the resulting heterogeneous graphs that represent typical NSL
learning problems. We show that our approach
outperforms the state-of-the-art on 3 NSL tasks: CORA, MUTA188 and MovieLens.

Publication Type:	Conference or Workshop Item (Paper)
Additional Information:	This article has been published in its final form by AAAI and it's available online at: https://doi.org/10.1609/aaai.v35i18.17898
Publisher Keywords:	Neuro-symbolic, Graph Neural Network, Inductive Logic Programming, Inductive Learning, Knowledge Graphs, Relational Learning, Heterogeneous Graphs
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Departments:	School of Science & Technology School of Science & Technology > Computer Science
SWORD Depositor:	Symplectic Administrator

Export

Downloads