Zeitschriftenartikel
Interactive Transfer Learning in Relational Domains
Vorschaubild nicht verfügbar
Volltext URI
Dokumententyp
Text/Journal Article
Zusatzinformation
Datum
2020
Zeitschriftentitel
ISSN der Zeitschrift
Bandtitel
Verlag
Springer
Zusammenfassung
We consider the problem of interactive transfer learning where a human expert provides guidance to the transfer learning algorithm that aims to transfer knowledge from a source task to a target task. One of the salient features of our approach is that we consider cross-domain transfer, i.e., transfer of knowledge across unrelated domains. We present an intuitive interface that allows for an expert to refine the knowledge in target task based on his/her expertise. Our results show that such guided transfer can effectively reduce the search space thus improving the efficiency and effectiveness of the transfer process.