File(s) under permanent embargo
Compositional neural logic programming
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.
History
Publication title
Proceedings of the 30th International Joint Conference on Artificial IntelligenceEditors
Z-H ZhouPagination
3059-3066ISBN
978-0-9992411-9-6Department/School
School of Information and Communication TechnologyPublisher
International Joint Conferences on Artificial Intelligence OrganizationPlace of publication
United StatesEvent title
30th International Joint Conference on Artificial IntelligenceEvent Venue
Virtual Conference, Online (Montreal, Canada)Date of Event (Start Date)
2021-08-19Date of Event (End Date)
2021-08-26Rights statement
Copyright 2021 International Joint Conferences on Artificial IntelligenceRepository Status
- Restricted