Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

PRISM: Topology-Aware Cross-Modal Imputation for Modality-Deficient Federated Graph Learning

About

Multimodal federated graph learning (MM-FGL) aims to collaboratively learn from decentralized graphs with text and images. However, real-world clients may not share a common modality basis: a visual-search client may contain image--interaction graphs but no seller descriptions, while a catalog client may provide text but no product images. We refer to this practical setting as client-level modality deficiency. Unlike random instance-wise missingness, a deficient client lacks the local semantic basis needed to reconstruct the absent modality. More importantly, in graph learning, incomplete representations initialize message passing, so imputation errors can be filtered, mixed, and amplified by the receiving topology. To address this gap, we propose \textbf{PRISM} (\textbf{P}roactive \textbf{R}etrieval and \textbf{I}mputation via \textbf{S}tructural \textbf{M}eta-prompting), a topology-aware federated cross-modal imputation framework. Rather than reconstructing the missing modality solely from local observations, PRISM recovers missing-modality semantics from the federation and introduces them into local graph propagation under topology-aware control. Experiments on six multimodal graph datasets across graph-centric and modality-centric tasks show that PRISM consistently improves modality-deficient clients, outperforming state-of-the-art baselines by \textbf{4.48}\% on average.

Zekai Chen, Miao Zhang, Jiayang Xing, Xunkai Li, Xun Wu, Rong-Hua Li, Guoren Wang• 2026

Related benchmarks

TaskDatasetResultRank
Node ClassificationGrocery
Accuracy79.64
139
Node ClassificationToys
Accuracy80.65
77
Modality RetrievalQB (Full)
R@587.26
25
Modality MatchingKU (Full)
AUC74.94
15
Modality MatchingKU (Miss)
AUC66.51
15
Modality MatchingBili Food (Full)
AUC72.59
15
Modality MatchingBili Food (Miss)
AUC63.14
15
Modality RetrievalQB (Miss)
R@577.25
15
Modality RetrievalCartoon (Full)
R@585.46
15
Modality RetrievalCartoon (Miss)
R@576.25
15
Showing 10 of 12 rows

Other info

Follow for update