Continual learning of knowledge graph embeddings

Angel Daruna, Mehul Gupta, Mohan Sridharan, Sonia Chernova

Research output: Contribution to journalArticlepeer-review

60 Downloads (Pure)


In recent years, there has been a resurgence in methods that use distributed (neural) representations to represent and reason about semantic knowledge for robotics applications. However, while robots often observe previously unknown concepts, these representations typically assume that all concepts are known a priori, and incorporating new information requires all concepts to be learned afresh. Our work relaxes this limiting assumption of existing representations and tackles the incremental knowledge graph embedding problem by leveraging the principles of a range of continual learning methods. Through an experimental evaluation with several knowledge graphs and embedding representations, we provide insights about trade-offs for practitioners to match a semantics-driven robotics applications to a suitable continual knowledge graph embedding method.
Original languageEnglish
Pages (from-to)1128-1135
Number of pages8
JournalIEEE Robotics and Automation Letters
Issue number2
Early online date1 Feb 2021
Publication statusPublished - Apr 2021


  • Continual learning
  • representation learning


Dive into the research topics of 'Continual learning of knowledge graph embeddings'. Together they form a unique fingerprint.

Cite this