Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhang, Jiahao, Wang, Lin, Wang, Shijie, Fan, Wenqi
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2403.07353
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910365602807808
author Zhang, Jiahao
Wang, Lin
Wang, Shijie
Fan, Wenqi
author_facet Zhang, Jiahao
Wang, Lin
Wang, Shijie
Fan, Wenqi
contents Graph Neural Networks (GNNs) have achieved remarkable success in various real-world applications. However, GNNs may be trained on undesirable graph data, which can degrade their performance and reliability. To enable trained GNNs to efficiently unlearn unwanted data, a desirable solution is retraining-based graph unlearning, which partitions the training graph into subgraphs and trains sub-models on them, allowing fast unlearning through partial retraining. However, the graph partition process causes information loss in the training graph, resulting in the low model utility of sub-GNN models. In this paper, we propose GraphRevoker, a novel graph unlearning framework that better maintains the model utility of unlearnable GNNs. Specifically, we preserve the graph property with graph property-aware sharding and effectively aggregate the sub-GNN models for prediction with graph contrastive sub-model aggregation. We conduct extensive experiments to demonstrate the superiority of our proposed approach.
format Preprint
id arxiv_https___arxiv_org_abs_2403_07353
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Graph Unlearning with Efficient Partial Retraining
Zhang, Jiahao
Wang, Lin
Wang, Shijie
Fan, Wenqi
Machine Learning
Cryptography and Security
Graph Neural Networks (GNNs) have achieved remarkable success in various real-world applications. However, GNNs may be trained on undesirable graph data, which can degrade their performance and reliability. To enable trained GNNs to efficiently unlearn unwanted data, a desirable solution is retraining-based graph unlearning, which partitions the training graph into subgraphs and trains sub-models on them, allowing fast unlearning through partial retraining. However, the graph partition process causes information loss in the training graph, resulting in the low model utility of sub-GNN models. In this paper, we propose GraphRevoker, a novel graph unlearning framework that better maintains the model utility of unlearnable GNNs. Specifically, we preserve the graph property with graph property-aware sharding and effectively aggregate the sub-GNN models for prediction with graph contrastive sub-model aggregation. We conduct extensive experiments to demonstrate the superiority of our proposed approach.
title Graph Unlearning with Efficient Partial Retraining
topic Machine Learning
Cryptography and Security
url https://arxiv.org/abs/2403.07353