Continual Learning of Knowledge Graph Embeddings

• Published in: IEEE robotics and automation letters Vol. 6; no. 2; pp. 1128 - 1135
• Main Authors: Daruna, Angel, Gupta, Mehul, Sridharan, Mohan, Chernova, Sonia
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01-04-2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Continual learning; Embedding; Graphical representations; Knowledge engineering; Knowledge representation; Learning; Learning systems; Neural networks; representation learning; Robotics; Robots; Semantics; Task analysis; Training
• ISSN: 2377-3766; 2377-3766
• DOI: 10.1109/LRA.2021.3056071

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.