Graph unlearning, which involves deleting graph elements such as nodes, node labels, and relationships from a trained graph neural network (GNN) model, is crucial for real-world applications where data elements may become irrelevant, inaccurate, or privacy-sensitive. However, existing methods for graph unlearning either deteriorate model weights shared across all nodes or fail to effectively delete edges due to their strong dependence on local graph neighborhoods. To address these limitations, we introduce GNNDelete, a novel model-agnostic layer-wise operator that optimizes two critical properties, namely, Deleted Edge Consistency and Neighborhood Influence, for graph unlearning. Deleted Edge Consistency ensures that the influence of deleted elements is removed from both model weights and neighboring representations, while Neighborhood Influence guarantees that the remaining model knowledge is preserved after deletion. GNNDelete updates representations to delete nodes and edges from the model while retaining the rest of the learned knowledge. We conduct experiments on seven real-world graphs, showing that GNNDelete outperforms existing approaches by up to 38.8% (AUC) on edge, node, and node feature deletion tasks, and 32.2% on distinguishing deleted edges from non-deleted ones. Additionally, GNNDelete is efficient, taking 12.3x less time and 9.3x less space than retraining GNN from scratch on WordNet18.

翻译：图遗忘学习涉及从已训练的图神经网络（GNN）模型中删除节点、节点标签和关系等图元素，对于数据元素可能变得不相关、不准确或涉及隐私的实际应用至关重要。然而，现有的图遗忘学习方法要么会损坏所有节点共享的模型权重，要么由于对局部图邻域的高度依赖而无法有效删除边。为解决这些局限性，我们提出了GNNDelete——一种新颖的与模型无关的层间算子，该算子针对图遗忘学习优化了两个关键性质，即删除边一致性（Deleted Edge Consistency）与邻域影响（Neighborhood Influence）。删除边一致性确保已删除元素的影响从模型权重和邻域表示中同时移除，而邻域影响则保证删除后保留的模型知识得以维持。GNNDelete通过更新表示来从模型中删除节点和边，同时保留其余已习得知识。我们在七个真实世界图上进行实验，结果表明：在边、节点及节点特征删除任务中，GNNDelete的性能（以AUC衡量）比现有方法最高提升38.8%；在区分已删除边与未删除边的任务中，性能提升32.2%。此外，GNNDelete具有高效性：在WordNet18数据集上，与从头重新训练GNN相比，其耗时减少12.3倍，空间占用减少9.3倍。