Adaptive Graph Unlearning

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ding, Pengfei, Wang, Yan, Liu, Guanfeng, Zhu, Jiajie
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910951800832000
author Ding, Pengfei
Wang, Yan
Liu, Guanfeng
Zhu, Jiajie
author_facet Ding, Pengfei
Wang, Yan
Liu, Guanfeng
Zhu, Jiajie
contents Graph unlearning, which deletes graph elements such as nodes and edges from trained graph neural networks (GNNs), is crucial for real-world applications where graph data may contain outdated, inaccurate, or privacy-sensitive information. However, existing methods often suffer from (1) incomplete or over unlearning due to neglecting the distinct objectives of different unlearning tasks, and (2) inaccurate identification of neighbors affected by deleted elements across various GNN architectures. To address these limitations, we propose AGU, a novel Adaptive Graph Unlearning framework that flexibly adapts to diverse unlearning tasks and GNN architectures. AGU ensures the complete forgetting of deleted elements while preserving the integrity of the remaining graph. It also accurately identifies affected neighbors for each GNN architecture and prioritizes important ones to enhance unlearning performance. Extensive experiments on seven real-world graphs demonstrate that AGU outperforms existing methods in terms of effectiveness, efficiency, and unlearning capability.
format Preprint
id arxiv_https___arxiv_org_abs_2505_12614
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Adaptive Graph Unlearning
Ding, Pengfei
Wang, Yan
Liu, Guanfeng
Zhu, Jiajie
Machine Learning
Graph unlearning, which deletes graph elements such as nodes and edges from trained graph neural networks (GNNs), is crucial for real-world applications where graph data may contain outdated, inaccurate, or privacy-sensitive information. However, existing methods often suffer from (1) incomplete or over unlearning due to neglecting the distinct objectives of different unlearning tasks, and (2) inaccurate identification of neighbors affected by deleted elements across various GNN architectures. To address these limitations, we propose AGU, a novel Adaptive Graph Unlearning framework that flexibly adapts to diverse unlearning tasks and GNN architectures. AGU ensures the complete forgetting of deleted elements while preserving the integrity of the remaining graph. It also accurately identifies affected neighbors for each GNN architecture and prioritizes important ones to enhance unlearning performance. Extensive experiments on seven real-world graphs demonstrate that AGU outperforms existing methods in terms of effectiveness, efficiency, and unlearning capability.
title Adaptive Graph Unlearning
topic Machine Learning
url https://arxiv.org/abs/2505.12614