Learn to Unlearn: Meta-Learning-Based Knowledge Graph Embedding Unlearning

Knowledge graph (KG) embedding methods map entities and relations from knowledge graphs to continuous vector spaces, simplifying their representations and enhancing performance across various tasks (e.g., link prediction, question answering). As concerns about personal privacy rise, machine unlearning (MU), an emerging AI technology that enables models to eliminate the influence of specific data, has garnered increasing attention from the academic community. Existing works typically achieves machine unlearning through data obfuscation and adjustments to the model's training loss. Furthermore, existing approaches lack generalization ability across different unlearning tasks. In this paper, we propose a Meta-Learning-Based Knowledge Graph Embedding Unlearning framework (MetaEU), specifically designed for KG embedding unlearning. By leveraging meta-learning, we generate embeddings that require unlearning. This process reduces the impact of specific knowledge on the graph while maintaining the model's performance on the remaining data. A thorough experimental study on benchmark datasets shows that MetaEU demonstrates promising performance in the knowledge graph embedding unlearning task.