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 how 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 on CORA, MUTA188 and MovieLens our approach outperforms the state-of-the-art in NSL.

Publication Type:	Conference or Workshop Item (Paper)
Additional Information:	Copyright © 2021, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Departments:	School of Science & Technology > Computer Science

Preview

Text - Accepted Version Download (156kB) | Preview

Export

Downloads