aiqbench analysis
MMFGU introduces a novel framework for multimodal federated graph unlearning, addressing the specific challenge of removing fine-grained data traces across heterogeneous signals like text and images without compromising global model utility. By decoupling target representations from retained semantics, this approach enables precise erasure requests while preventing information leakage through remaining modalities or neighboring nodes in a distributed setting. The method achieves significant efficiency gains with a 41.5x speedup over full retraining, offering practical solutions for privacy-preserving updates in complex graph-based AI systems.
MMFGU: Multimodal Federated Graph Unlearning
arXiv:2607.28708v1 Announce Type: new Abstract: Multimodal federated graph learning enables clients to collaboratively train graph models over structural, textual, and visual signals without sharing private local data. However, the presence of heterogeneous multimodal content also makes unlearning requests more frequent and fine-grained: users may delete accounts or interactions, remove a particular image or text while retaining the associated entity, or revoke the learned correspondence between retained modalities or graph attributes. Existing federated graph unlearning mainly handles entity/relation or client removal and cannot directly satisfy these multimodal requests. They introduce three challenges: removing only the requested information without damaging retained content, preventing the target from being recovered through remaining modalities or graph neighborhoods, and stopping related traces on other clients from re-entering the global model after aggregation. To address them, we propose \textsc{\textbf{MMFGU}}, a multimodal federated graph unlearning framework built around target-specific representation decoupling. \textsc{MMFGU} maps heterogeneous requests into unified target carriers, decouples requested representations while anchoring retained semantics, exposes and repairs propagated residuals with lightweight probes, and selectively purges affected clients through compact prototype and response signals. Experiments show that \textsc{MMFGU} effectively removes requested information, preserves retained graph utility, and achieves a $\boldsymbol{41.5\times}$ speedup over full retraining.
Abstract:Multimodal federated graph learning enables clients to collaboratively train graph models over structural, textual, and visual signals without sharing private local data. However, the presence of heterogeneous multimodal content also makes unlearning requests more frequent and fine-grained: users may delete accounts or interactions, remove a particular image or text while retaining the associated entity, or revoke the learned correspondence between retained modalities or graph attributes. Existing federated graph unlearning mainly handles entity/relation or client removal and cannot directly satisfy these multimodal requests. They introduce three challenges: removing only the requested information without damaging retained content, preventing the target from being recovered through remaining modalities or graph neighborhoods, and stopping related traces on other clients from re-entering the global model after aggregation. To address them, we propose \textsc{\textbf{MMFGU}}, a multimodal federated graph unlearning framework built around target-specific representation decoupling. \textsc{MMFGU} maps heterogeneous requests into unified target carriers, decouples requested representations while anchoring retained semantics, exposes and repairs propagated residuals with lightweight probes, and selectively purges affected clients through compact prototype and response signals. Experiments show that \textsc{MMFGU} effectively removes requested information, preserves retained graph utility, and achieves a $\boldsymbol{41.5\times}$ speedup over full retraining.
Machine Learning (cs.LG)
arXiv:2607.28708 [cs.LG]
(or arXiv:2607.28708v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2607.28708 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 286 words
Related coverage
Toward Federated Multimodal Graph Foundation Models: A Topology-Aware Multimodal Alignment Framework
arXiv · Jul 20, 2026
Coupling Perception and Reasoning in Federated Multimodal Graph Foundation Models
arXiv · Oct 2, 2026
FedOGL: Combating Catastrophic Forgetting in Federated Open-World Multimodal Graph Learning
arXiv · Jul 31, 2026
Towards Effective Federated Multimodal Graph Learning via Navigating Multifaceted Heterogeneity
arXiv · Aug 4, 2026