Cardiff University | Prifysgol Caerdydd ORCA
Online Research @ Cardiff 
WelshClear Cookie - decide language by browser settings

Stacked structure learning for lifted relational neural networks

Sourek, Gustav, Svatos, Martin, Zelezny, Filip, Schockaert, Steven ORCID: and Kuzelka, Ondrej 2018. Stacked structure learning for lifted relational neural networks. Presented at: International Conference on Inductive Logic Programming, Orléans, France, 4- 6 September 2017. Published in: Lachiche, Nicholas and Vrain, Christel eds. Inductive Logic Programming. Lecture Notes in Computer Science (10759) Springer, pp. 140-151. 10.1007/978-3-319-78090-0_10

[thumbnail of Structure_Learning_ILP2017.pdf]
PDF - Accepted Post-Print Version
Download (1MB) | Preview


Lifted Relational Neural Networks (LRNNs) describe relational domains using weighted first-order rules which act as templates for constructing feed-forward neural networks. While previous work has shown that using LRNNs can lead to state-of-the-art results in various ILP tasks, these results depended on hand-crafted rules. In this paper, we extend the framework of LRNNs with structure learning, thus enabling a fully automated learning process. Similarly to many ILP methods, our structure learning algorithm proceeds in an iterative fashion by top-down searching through the hypothesis space of all possible Horn clauses, considering the predicates that occur in the training examples as well as invented soft concepts entailed by the best weighted rules found so far. In the experiments, we demonstrate the ability to automatically induce useful hierarchical soft concepts leading to deep LRNNs with a competitive predictive power.

Item Type: Conference or Workshop Item (Paper)
Date Type: Published Online
Status: Published
Schools: Computer Science & Informatics
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Publisher: Springer
ISBN: 9783319780894
Funders: ERC
Related URLs:
Date of First Compliant Deposit: 12 July 2017
Date of Acceptance: 9 June 2017
Last Modified: 02 Nov 2022 11:32

Citation Data

Cited 3 times in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item Edit Item


Downloads per month over past year

View more statistics