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

Source: [Learn to Unlearn: Meta-Learning-Based Knowledge Graph Embedding Unlearning](<https://www.sota2.com/research/paper/68fa76051e209131cea6af85>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T03:45:34.560Z

Authors: Naixing Xu, Qian Li, Xu Wang, Bingchen Liu, Xin Li

Published: 2024-12-01T16:43:04.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2412.00881>)

[PDF](<https://arxiv.org/pdf/2412.00881.pdf>)
