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

TL;DR

This paper introduces MetaEU, a meta-learning framework for knowledge graph embedding unlearning, enabling models to efficiently forget specific data points while maintaining overall performance, addressing privacy concerns.

Contribution

The paper presents a novel meta-learning approach for knowledge graph unlearning, which generalizes better across tasks compared to existing data obfuscation methods.

Findings

MetaEU effectively unlearns specific embeddings in KG models.

It preserves overall model performance after unlearning.

Experimental results show superior unlearning efficiency on benchmark datasets.

Abstract

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.