Continual Learning of Knowledge Graph Embeddings

TL;DR

This paper addresses the challenge of updating knowledge graph embeddings incrementally in robotics, proposing methods that allow models to learn new concepts without retraining from scratch, thus improving adaptability.

Contribution

It introduces a continual learning framework for knowledge graph embeddings, enabling incremental updates and reducing retraining costs in robotics applications.

Findings

Different continual learning methods have varying trade-offs in accuracy and efficiency.

The proposed approaches improve the ability to incorporate new concepts in knowledge graphs.

Insights help practitioners select suitable continual embedding methods for robotics.

Abstract

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.