Learn to Unlearn: Meta-Learning-Based Knowledge Graph Embedding Unlearning
This addresses privacy concerns in AI by providing a method for machine unlearning in knowledge graphs, though it appears incremental as it builds on existing unlearning techniques with a meta-learning twist.
The paper tackled the problem of enabling knowledge graph embedding models to forget specific data for privacy, introducing MetaEU, a meta-learning-based framework that effectively unlearns targeted embeddings while maintaining performance on the remaining data.
Knowledge graph (KG) embedding methods map entities and relations into continuous vector spaces, improving performance in tasks like link prediction and question answering. With rising privacy concerns, machine unlearning (MU) has emerged as a critical AI technology, enabling models to eliminate the influence of specific data. Existing MU approaches often rely on data obfuscation and adjustments to training loss but lack generalization across unlearning tasks. This paper introduces MetaEU, a Meta-Learning-Based Knowledge Graph Embedding Unlearning framework. MetaEU leverages meta-learning to unlearn specific embeddings, mitigating their impact while preserving model performance on remaining data. Experiments on benchmark datasets demonstrate its effectiveness in KG embedding unlearning.