City Research Online

Coherent and Consistent Relational Transfer Learning with Auto-encoders

Stromfelt, H., Dickens, L., d'Avila Garcez, A. S. & Russo, A. (2021). Coherent and Consistent Relational Transfer Learning with Auto-encoders. Proceedings of the 15th International Workshop on Neural-Symbolic Learning and Reasoning (NeSy 2021), 2986, pp. 176-192. ISSN 1613-0073


Human defined concepts are inherently transferable, but it is not clear under what conditions they can be modelled effectively by non-symbolic artificial learners. This paper argues that for a transferable concept to be learned, the system of relations that define it must be coherent across domains and properties. That is, they should be consistent with respect to relational constraints, and this consistency must extend beyond the representations encountered in the source domain. Further, where relations are modelled by differentiable functions, their gradients must conform – the functions must at times move together to preserve consistency. We propose a Partial Relation Transfer (PRT) task which exposes how well relation-decoders model these properties, and exemplify this with ordinality prediction transfer task, including a new data set for the transfer domain. We evaluate this on existing relation-decoder models, as well as a novel model designed around the principles of consistency and gradient conformity. Results show that consistency across broad regions of input space indicates good transfer performance, and that good gradient conformity facilitates consistency.

Publication Type: Conference or Workshop Item (Paper)
Additional Information: Copyright © 2021 the authors. Published under the Creative Commons License Attribution 4.0 International (CC BY 4.0).
Publisher Keywords: Representation Learning; Relation Learning; Variational AutoEncoders; Concept Learning
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Departments: School of Science & Technology > Computer Science
[thumbnail of paper14.pdf]
Text - Published Version
Available under License Creative Commons Attribution.

Download (1MB) | Preview


Add to AnyAdd to TwitterAdd to FacebookAdd to LinkedinAdd to PinterestAdd to Email


Downloads per month over past year

View more statistics

Actions (login required)

Admin Login Admin Login