LAUSR

Hypergraph Unlearning: A Size-Based Hyperedge Selection and Coverage Aggregation Approach

Sign Up to like & get
recommendations!
0 Published in 2025 at "IEEE Transactions on Information Forensics and Security"

DOI: 10.1109/tifs.2025.3580218

Abstract: Graph unlearning aims to provably remove some training data from graph neural networks (GNNs) while eliminating their impact on model predictions. Although retraining the GNNs from scratch is a direct and legitimate solution, it entails… read more here.

Keywords: graph unlearning; coverage; hypergraph unlearning; size based ... See more keywords