Search papers, labs, and topics across Lattice.
This paper addresses the problem of catastrophic utility degradation in multimodal graph unlearning by observing that uniformly editing parameters across GNN layers, especially high-dimensional input projections, is detrimental. They propose FDQ, a Feature-Dimension Aware Quantile framework, which adaptively identifies sensitive high-dimensional input projection layers and applies conservative quantile thresholds during suppression set construction. Experiments on Ele-Fashion and Goodreads-NC demonstrate that FDQ achieves strong utility preservation while maintaining effective forgetting against membership inference attacks.
Multimodal graph unlearning doesn't have to destroy utility: carefully protecting high-dimensional input projections during the unlearning process preserves performance while still enabling effective forgetting.
Graph unlearning remains a critical technique for supporting privacy-preserving and sustainable multimodal graph learning. However, we observe that existing unlearning strategies tend to apply uniform parameter selection and editing across all graph neural network (GNN) layers, which is especially harmful for multimodal graphs where high-dimensional input projections encode dominant cross-modal knowledge. As a result, over-editing these sensitive layers often leads to catastrophic utility degradation after forgetting, undermining both stable learning and effective privacy protection. To address this gap, we propose FDQ, a Feature-Dimension Aware Quantile framework for multimodal graph unlearning. FDQ adaptively identifies high-dimensional input projection layers and applies more conservative, FDQ-guided quantile thresholds when constructing suppression sets, while keeping the underlying importance estimation mechanism unchanged. FDQ is seamlessly integrated with diagonal sensitivity-based parameter importance analysis to enable efficient node and edge unlearning under general forget requests. Through extensive experiments on Ele-Fashion and Goodreads-NC, we demonstrate that FDQ consistently achieves strong utility preservation while maintaining effective forgetting against membership inference attacks. Overall, FDQ offers a principled and robust solution for privacy-aware unlearning in high-dimensional multimodal graph systems.
