
The author introduces a novel method, Unlink to Unlearn (UtU), to simplify edge unlearning in Graph Neural Networks by exclusively unlinking forget edges from the graph structure. This approach aims to address over-forgetting issues while maintaining high accuracy and privacy protection capabilities.


coremsg

unlink-to-unlearn-simplifying-edge-unlearning-in-gnns


Unlink to Unlearn: Simplifying Edge Unlearning in GNNs


title_rewrite


GNNDelete's loss functions contribute to over-forgetting, leading to the development of a simplified approach, UtU, for effective edge unlearning.
