Continual Learning of Knowledge Graph Embeddings
This addresses the challenge of updating semantic knowledge in robotics as new concepts are observed, though it appears incremental by applying existing continual learning techniques to knowledge graphs.
The paper tackles the problem of incremental knowledge graph embedding for robotics, where existing methods assume all concepts are known beforehand, and shows that leveraging continual learning methods can incorporate new information without relearning everything, providing insights on trade-offs for practitioners.
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.