FedGAMMA: A Federated Multimodal Graph Foundation Model with Topology-Aware Alignment
Researchers introduce FedGAMMA, a framework for federated learning on multimodal-attributed graphs, which enables collaborative model training across privacy-restricted data silos without sharing raw data. The approach uses a two-stage process involving federated pre-training and prompt-based fine-tuning, incorporating topology-aware alignment and semantic-structural disentanglement. Experiments on twelve datasets show FedGAMMA achieving up to 12.96% improvement over existing baselines.
Why it matters: This work enables effective federated learning on complex multimodal graph data while preserving privacy, advancing collaborative AI in sensitive domains.
Full story at: arXiv Machine Learning ↗