VC-dimension based generalization bounds for relational learning

Kuzelka, Ondrej, Wang, Yuyi and Schockaert, Steven ORCID: https://orcid.org/0000-0002-9256-2881 2018. VC-dimension based generalization bounds for relational learning. Presented at: ECML-PKDD 2018: European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, Dublin, Ireland, 10-14 Sept 2018.

Preview

PDF - Accepted Post-Print Version Download (331kB) | Preview

Abstract

In many applications of relational learning, the available data can be seen as a sample from a larger relational structure (e.g. we may be given a small fragment from some social network). In this paper we are particularly concerned with scenarios in which we can assume that (i) the domain elements appearing in the given sample have been uniformly sampled without replacement from the (unknown) full domain and (ii) the sample is complete for these domain elements (i.e. it is the full substructure induced by these elements). Within this setting, we study bounds on the error of sufficient statistics of relational models that are estimated on the available data. As our main result, we prove a bound based on a variant of the Vapnik-Chervonenkis dimension which is suitable for relational data.

Item Type:	Conference or Workshop Item (Paper)
Date Type:	Completion
Status:	In Press
Schools:	Computer Science & Informatics
Related URLs:	Organisation
Date of First Compliant Deposit:	23 July 2018
Last Modified:	23 Oct 2022 14:17
URI:	https://orca.cardiff.ac.uk/id/eprint/113249

Actions (repository staff only)

Edit Item