Preprint
Aug 2026
Towards Effective Federated Multimodal Graph Learning via Navigating Multifaceted Heterogeneity
Federated multimodal graph learning with Topology-aware Cross-modal Routing (FedTCR) is proposed, the first systematic algorithm designed for FMGL and outperforms state-of-the-art baselines on both graph-centric and modality-centric tasks.
Yin-Lin Zhu, Di Wu, Yi Zhang et al.
· 1 citation