eCite Digital Repository

Compositional neural logic programming


Tran, SN, Compositional neural logic programming, Proceedings of the 30th International Joint Conference on Artificial Intelligence, 19-26 August 2021, Virtual Conference, Online (Montreal, Canada), pp. 3059-3066. ISBN 978-0-9992411-9-6 (2021) [Refereed Conference Paper]

Copyright Statement

Copyright 2021 International Joint Conferences on Artificial Intelligence

DOI: doi:10.24963/ijcai.2021/421


This paper introduces Compositional Neural Logic Programming (CNLP), a framework that integrates neural networks and logic programming for symbolic and sub-symbolic reasoning. We adopt the idea of compositional neural networks to represent first-order logic predicates and rules. A voting backward-forward chaining algorithm is proposed for inference with both symbolic and sub-symbolic variables in an argument-retrieval style. The framework is highly flexible in that it can be constructed incrementally with new knowledge, and it also supports batch reasoning in certain cases. In the experiments, we demonstrate the advantages of CNLP in discriminative tasks and generative tasks.

Item Details

Item Type:Refereed Conference Paper
Keywords:deep learning, reasoning
Research Division:Information and Computing Sciences
Research Group:Artificial intelligence
Research Field:Knowledge representation and reasoning
Objective Division:Information and Communication Services
Objective Group:Information systems, technologies and services
Objective Field:Artificial intelligence
UTAS Author:Tran, SN (Dr Son Tran)
ID Code:146293
Year Published:2021
Deposited By:Information and Communication Technology
Deposited On:2021-08-27
Last Modified:2022-05-18

Repository Staff Only: item control page