mlsanityData to 7 Oct 2026

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

arXiv 2606.09301 ↗First posted 8 Jun 2026cs.LGcited by 3

Not on the map. Why?

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.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 26 of its 35 references that are in the map. First posted on arXiv 8 Jun 2026.

Builds on

26 of 35 references.

References · 26

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  4. 2017Graph Attention Networkscited by 8,854
  5. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  6. 2017Inductive Representation Learning on Large Graphscited by 6,284
  7. 2018How Powerful are Graph Neural Networks?cited by 4,355
  8. 2022GraphMAE: Self-Supervised Masked Graph Autoencoderscited by 443
  9. 2021FedProto: Federated Prototype Learning across Heterogeneous Clientscited by 349
  10. 2022V2X-ViT: Vehicle-to-Everything Cooperative Perception with Vision Transformercited by 320
  11. 2022Where2comm: Communication-Efficient Collaborative Perception via Spatial Confidence Mapscited by 255
  12. 2021Subgraph Federated Learning with Missing Neighbor Generationcited by 132
14 more
  1. 2022Graph Neural Networks in IoT: A Surveycited by 27
  2. 2024When Graph meets Multimodal: Benchmarking and Meditating on Multimodal Attributed Graphs Learningcited by 20
  3. 2023NineRec: A Benchmark Dataset Suite for Evaluating Transferable Recommendationcited by 18
  4. 2024OpenFGL: A Comprehensive Benchmark for Federated Graph Learningcited by 16
  5. 2024FedMAC: Tackling Partial-Modality Missing in Federated Learning with Cross-Modal Aggregation and Contrastive Regularizationcited by 16
  6. 2024Deep Efficient Private Neighbor Generation for Subgraph Federated Learningcited by 14
  7. 2024Modeling Inter-Intra Heterogeneity for Graph Federated Learningcited by 12
  8. 2026MM-OpenFGL: A Comprehensive Benchmark for Multimodal Federated Graph Learningcited by 11
  9. 2024MGNet: Learning Correspondences via Multiple Graphscited by 10
  10. 2025S2FGL: Spatial Spectral Federated Graph Learningcited by 7
  11. 2025Subgraph Federated Learning via Spectral Methodscited by 6
  12. 2024MH-pFLGB: Model Heterogeneous personalized Federated Learning via Global Bypass for Medical Image Analysiscited by 4
  13. 2025FedMVP: Federated Multimodal Visual Prompt Tuning for Vision-Language Modelscited by 4
  14. 2025Rethinking Client-oriented Federated Graph Learningcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026FedLAB: Traceable Semantic Codebooks for Federated Multimodal Graph Foundation Learningcited by 1
  2. 2026FedOGL: Combating Catastrophic Forgetting in Federated Open-World Multimodal Graph Learningcited by 0
  3. 2026Coupling Perception and Reasoning in Federated Multimodal Graph Foundation Modelscited by 0