Our implementations are available at \url. We conduct extensive experiments on four representative GNN models and three benchmark datasets to justify the superiority of GIF for diverse graph unlearning tasks in terms of unlearning efficacy, model utility, and unlearning efficiency. Further deductions on the closed-form solution of parameter changes provide a better understanding of the unlearning mechanism. The idea is to supplement the objective of the traditional influence function with an additional loss term of the influenced neighbors due to the structural dependency. Then, we recognize the crux to the inability of traditional influence function for graph unlearning, and devise Graph Influence Function (GIF), a model-agnostic unlearning method that can efficiently and accurately estimate parameter changes in response to a $\epsilon$-mass perturbation in deleted data. We first present a unified problem formulation of diverse graph unlearning tasks \wrt node, edge, and feature. Details File Size: 265KB Duration: 9. Discover and Share the best GIFs on Tenor. In this work, we explore the influence function tailored for graph unlearning, so as to improve the unlearning efficacy and efficiency for graph unlearning. The perfect Neural Network Machine Learning Animated GIF for your conversation. However, ranging from machine unlearning to recently emerged graph unlearning methods, existing efforts either resort to retraining paradigm, or perform approximate erasure that fails to consider the inter-dependency between connected neighbors or imposes constraints on GNN structure, therefore hard to achieve satisfying performance-complexity trade-offs. Download a PDF of the paper titled GIF: A General Graph Unlearning Strategy via Influence Function, by Jiancan Wu and 5 other authors Download PDF Abstract:With the greater emphasis on privacy and security in our society, the problem of graph unlearning - revoking the influence of specific data on the trained GNN model, is drawing increasing attention.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |