Learn to Unlearn: Meta-Learning-Based Knowledge Graph Embedding Unlearning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910722834825216 |
|---|---|
| author | Xu, Naixing Li, Qian Wang, Xu Liu, Bingchen Li, Xin |
| author_facet | Xu, Naixing Li, Qian Wang, Xu Liu, Bingchen Li, Xin |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_00881 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Learn to Unlearn: Meta-Learning-Based Knowledge Graph Embedding Unlearning Xu, Naixing Li, Qian Wang, Xu Liu, Bingchen Li, Xin Artificial Intelligence 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. |
| title | Learn to Unlearn: Meta-Learning-Based Knowledge Graph Embedding Unlearning |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2412.00881 |