Abstract
We summarize Linear Relational Embedding (LRE), a method which has been recently proposed for generalizing over relational data. We show that LRE can represent any binary relations, but that there are relations of arity greater than 2 that it cannot represent. We then introduce Non-Linear Relational Embedding (NLRE) and show that it can learn any relation. Results of NLRE on the Family Tree Problem show that generalization is much better than the one obtained using backpropagation on the same problem.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
G. E. Hinton, Implementing Semantic Networks in Parallel Hardware, in Parallel Models of Associative Memory, G.E. Hinton and J.A. Anderson eds, Erlbaum, 1981
G.E. Hinton, Learning Distributed Representations of Concepts, Proceedings of the Eighth Annual Conference of the Cognitive Science Society, Erlbaum, 1–12,1986
R. Miikkulainen and M. G. Dyer, Encoding input/output representations in connectionist cognitive systems in Proc. 1988 Conn. Models Summer School, 347–356.
A. Paccanaro and G. E. Hinton, Learning Distributed Representation of Concepts using Linear Relational Embedding, IEEE Trans. on Knowledge and Data Engineering, Vol. 13, N.2, 232–245, 2001
A. Paccanaro, G.E. Hinton, Learning Hierarchical Structures with Linear Relational Embedding, NIPS 14, MIT Press, Cambridge, MA, 2001
J.B. Pollack, Recursive Distributed Representations, Artificial Intelligence, vol. 46, 77–105, 1990
J.R. Quinlan, Learning logical definitions from relations, Machine Learning, 5, 239–266, 1990
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Paccanaro, A. (2003). Learning Distributed Representations of High-Arity Relational Data with Non-linear Relational Embedding. In: Kaynak, O., Alpaydin, E., Oja, E., Xu, L. (eds) Artificial Neural Networks and Neural Information Processing — ICANN/ICONIP 2003. ICANN ICONIP 2003 2003. Lecture Notes in Computer Science, vol 2714. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44989-2_19
Download citation
DOI: https://doi.org/10.1007/3-540-44989-2_19
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40408-8
Online ISBN: 978-3-540-44989-8
eBook Packages: Springer Book Archive