PRISM: Topology-Aware Cross-Modal Imputation for Modality-Deficient Federated Graph Learning
Researchers have introduced PRISM, a novel framework for federated graph learning that addresses the challenge of modality deficiency across different clients. PRISM enables collaborative learning from decentralized graphs containing text and images, even when individual clients lack complete multimodal data. The framework proactively retrieves and imputes missing modality semantics from the federation, integrating them into local graph propagation with topology-aware control. Experiments demonstrate PRISM's effectiveness, showing an average improvement of 4.48% over state-of-the-art baselines on six multimodal graph datasets. AI
IMPACT Enhances collaborative learning from decentralized multimodal data, potentially improving AI applications that rely on diverse data sources.