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

arXiv: https://arxiv.org/abs/2606.09301 · HTML: https://mlsanity.com/paper/2606.09301/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 35 references that are in the map.
- First posted on arXiv 8 Jun 2026.

## Builds on (most cited first, 26 of 26)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [GraphMAE: Self-Supervised Masked Graph Autoencoders](https://mlsanity.com/paper/2205.10803/) (2022)
- [FedProto: Federated Prototype Learning across Heterogeneous Clients](https://mlsanity.com/paper/2105.00243/) (2021)
- [V2X-ViT: Vehicle-to-Everything Cooperative Perception with Vision Transformer](https://mlsanity.com/paper/2203.10638/) (2022)
- [Where2comm: Communication-Efficient Collaborative Perception via Spatial Confidence Maps](https://mlsanity.com/paper/2209.12836/) (2022)
- [Subgraph Federated Learning with Missing Neighbor Generation](https://mlsanity.com/paper/2106.13430/) (2021)
- [Graph Neural Networks in IoT: A Survey](https://mlsanity.com/paper/2203.15935/) (2022)
- [When Graph meets Multimodal: Benchmarking and Meditating on Multimodal Attributed Graphs Learning](https://mlsanity.com/paper/2410.09132/) (2024)
- [NineRec: A Benchmark Dataset Suite for Evaluating Transferable Recommendation](https://mlsanity.com/paper/2309.07705/) (2023)
- [OpenFGL: A Comprehensive Benchmark for Federated Graph Learning](https://mlsanity.com/paper/2408.16288/) (2024)
- [FedMAC: Tackling Partial-Modality Missing in Federated Learning with Cross-Modal Aggregation and Contrastive Regularization](https://mlsanity.com/paper/2410.03070/) (2024)
- [Deep Efficient Private Neighbor Generation for Subgraph Federated Learning](https://mlsanity.com/paper/2401.04336/) (2024)
- [Modeling Inter-Intra Heterogeneity for Graph Federated Learning](https://mlsanity.com/paper/2412.11402/) (2024)
- [MM-OpenFGL: A Comprehensive Benchmark for Multimodal Federated Graph Learning](https://mlsanity.com/paper/2601.22416/) (2026)
- [MGNet: Learning Correspondences via Multiple Graphs](https://mlsanity.com/paper/2401.04984/) (2024)
- [S2FGL: Spatial Spectral Federated Graph Learning](https://mlsanity.com/paper/2507.02409/) (2025)
- [Subgraph Federated Learning via Spectral Methods](https://mlsanity.com/paper/2510.25657/) (2025)
- [MH-pFLGB: Model Heterogeneous personalized Federated Learning via Global Bypass for Medical Image Analysis](https://mlsanity.com/paper/2407.00474/) (2024)
- [FedMVP: Federated Multimodal Visual Prompt Tuning for Vision-Language Models](https://mlsanity.com/paper/2504.20860/) (2025)
- [Rethinking Client-oriented Federated Graph Learning](https://mlsanity.com/paper/2504.14188/) (2025)

## Built on by (most cited first, 3 of 3)

- [FedLAB: Traceable Semantic Codebooks for Federated Multimodal Graph Foundation Learning](https://mlsanity.com/paper/2606.32016/) (2026)
- [FedOGL: Combating Catastrophic Forgetting in Federated Open-World Multimodal Graph Learning](https://mlsanity.com/paper/2607.27665/) (2026)
- [Coupling Perception and Reasoning in Federated Multimodal Graph Foundation Models](https://mlsanity.com/paper/2610.00277/) (2026)

## Abstract (arXiv)

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 PRISM (Proactive Retrieval and Imputation via Structural Meta-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 4.48% on average.