Unlink to Unlearn: Simplifying Edge Unlearning in GNNs

arXiv:2402.10695v1 Announce Type: new
Abstract: As concerns over data privacy intensify, unlearning in Graph Neural Networks (GNNs) has emerged as a prominent research frontier in academia. This concept is pivotal in enforcing the right to be forgotten, which entails the selective removal of specific data from trained GNNs upon user request. Our research focuses on edge unlearning, a process of particular relevance to real-world applications, owing to its widespread applicability. Current state-of-the-art approaches like GNNDelete can eliminate the influence of …

abstract academia arxiv concept concerns cs.ai cs.cr cs.lg data data privacy edge gnns graph graph neural networks networks neural networks pivotal privacy research simplifying type unlearning