Towards Modality-imbalanced Federated Graph Learning: A Data Synthesis-based Approach

2026-06-18

AI Summary

This work addresses the challenge of client-level or node-level modality missingness in multimodal federated graph learning by proposing FedMGS, a federated modality-aware graph synthesis framework. The method formulates modality imbalance as a graph-aware implicit semantic synthesis task, leveraging an availability-aware graph encoder, a prototype-guided implicit semantic synthesizer, and a reliability-calibrated fusion mechanism to reconstruct missing modality semantics in the representation space, align data distributions, and reduce variance. Notably, FedMGS is the first to enable cross-client semantic anchor–guided synthesis of missing modalities. Extensive experiments demonstrate its superior performance over state-of-the-art methods across four tasks, achieving gains of up to 17.41% while maintaining an optimal trade-off between efficiency and accuracy.

Abstract

MultiModal Federated Graph Learning (MM-FGL) offers a natural collaborative training paradigm, but its practical deployment is challenged by two granularities of modality imbalance. Client-level imbalance occurs when certain clients lack entire modalities, while node-level imbalance occurs when individual nodes exhibit missing visual or textual attributes. While several relevant studies exist, our investigation reveals that they predominantly target graph-agnostic or centralized scenarios, rendering them difficult to adapt directly. To address these challenges, we formalize modality-imbalanced MM-FGL as an implicit graph-aware latent semantic representation synthesis problem. This paradigm recovers missing modal semantics directly within the representation space, thereby maximizing alignment with the original data's semantic distribution and mitigating the high variance induced by missing modalities. To this end, we propose FedMGS (Federated Modality-aware Graph Synthesis), which integrates three core components. The availability-aware graph encoder prevents missing modalities from contaminating local structural propagation. The prototype-guided latent semantic synthesizer establishes cross-client semantic anchors for unavailable modalities. The reliability-calibrated semantic fusion mechanism regulates the impact of recovered latent representations prior to predictive readout. Extensive experiments on four tasks show that FedMGS consistently outperforms competitive baselines with gains up to 17.41% with best efficiency-performance tradeoff.

Problem

• Modality Imbalance
• Federated Graph Learning
• MultiModal Learning
• Missing Modalities
• Graph Representation

Innovation

• Federated Graph Learning
• Modality Imbalance
• Data Synthesis
• Latent Semantic Representation
• Cross-client Collaboration