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

2024-12-01 · Naixing Xu, Qian Li, Xu Wang, Bingchen Liu, Xin Li

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.

📄 PDF Abstract BibTeX arXiv:2412.00881

Code (0)

등록된 구현이 없습니다.

Tasks

Graph Embedding Knowledge Graph Embedding Link PredictionMachine UnlearningMeta-Learning Question Answering

Unlearning of Knowledge Graph Embedding via Preference Optimization

2025-07-28 · Jiajun Liu, Wenjun Ke, Peng Wang, Yao He 외 arxiv

Existing knowledge graphs (KGs) inevitably contain outdated or erroneous knowledge that needs to be removed from knowledge graph embedding (KGE) models. To address this challenge, knowledge unlearning can be applied to e…

Knowledge Graph Embedding Knowledge Graphs

Federated Graph Unlearning

2025-08-04 · Yuming Ai, Xunkai Li, Jiaqi Chao, Bowen Fan 외 arxiv

The demand for data privacy has led to the development of frameworks like Federated Graph Learning (FGL), which facilitate decentralized model training. However, a significant operational challenge in such systems is adh…

Graph Generation Graph Learning

Heterogeneous Federated Knowledge Graph Embedding Learning and Unlearning

2023-02-04 · Xiangrong Zhu, Guangyao Li, Wei Hu

Federated Learning (FL) recently emerges as a paradigm to train a global machine learning model across distributed clients without sharing raw data. Knowledge Graph (KG) embedding represents KGs in a continuous vector sp…

Federated Learning Graph Embedding Knowledge Distillation Knowledge Graph Embedding+1

Federated Knowledge Graph Unlearning via Diffusion Model

2024-03-13 · Bingchen Liu, Yuanyuan Fang

Federated learning (FL) promotes the development and application of artificial intelligence technologies by enabling model sharing and collaboration while safeguarding data privacy. Knowledge graph (KG) embedding represe…

Federated Learning Knowledge Graphs Machine Unlearning model

Node-level Contrastive Unlearning on Graph Neural Networks

2025-03-04 · Hong kyu Lee, Qiuchen Zhang, Carl Yang, Li Xiong

Graph unlearning aims to remove a subset of graph entities (i.e. nodes and edges) from a graph neural network (GNN) trained on the graph. Unlike machine unlearning for models trained on Euclidean-structured data, effecti…

Graph Neural Network graph partitioning Machine Unlearning