Towards Robust Federated Multimodal Graph Learning under Modality Heterogeneity

Sirui Zhang, Haonan Wang, Xunkai Li, Zekai Chen, Shumeng Li, Hongchao Qin, Rong-Hua Li, Guoren Wang

arXiv:2605.12584 · 2026-05-14 공개 · arXiv · PDF

federated-learning topology-aware missing-modality graph-learning non-iid expert-routing fedmpo multimodal-graph

Abstract

Recently, multimodal graph learning (MGL) has garnered significant attention for integrating diverse modality information and structured context to support various network applications. However, real-world graphs are often isolated due to data-sharing limitations across multiple parties, and their modalities are frequently incomplete. This highlights an urgent need to develop a robust federated approach. However, we find that existing methods remain insufficient. On the one hand, centralized MGL methods that handle missing modalities overlook the knowledge sharing and generalization in federated scenarios. On the other hand, while federated MGL methods have become increasingly mature, they primarily target non-graph data. Based on these technologies, we identify a two-stage pipeline wherein client-side completion reconstructs missing modalities, and server-side aggregation integrates the client-updated parameters of both the modality generator and the backbone models. Although this serves as a general solution, we identify two primary challenges in achieving greater robustness: (1) Topology-Isolated Local Completion: Client-side modality generation struggles to effectively leverage global semantics. (2) Reliability-Imbalanced Global Aggregation: Server-side multi-party collaboration is hindered by client updates with varying modality availability and recovery reliability. To address these challenges, we propose \textsc{FedMPO}, which utilizes topology-aware cross-modal generation to recover missing features using comprehensive graph context, missing-aware expert routing to locally filter out noisy recovered signals, and reliability-aware aggregation to appropriately down-weight unreliable updates. Extensive experiments on 3 tasks across 6 datasets demonstrate that FedMPO outperforms baselines, achieving performance gains of up to 4.10% and 5.65% in high-missing and non-IID settings.

한국어 요약

📋 한 줄 요약

**[연합 학습 / 멀티모달 그래프]** 모달리티 결손과 데이터 공유 제약이 공존하는 실세계 멀티모달 그래프 시나리오를 위한 강건한 연합 학습 프레임워크 FedMPO를 제안.

🎯 핵심 기여도

💡 핵심 아이디어

연합 멀티모달 그래프에서 강건성의 두 축은 (a) 결손 모달리티를 복원할 때 전역 그래프 의미를 활용하는 것과 (b) 클라이언트마다 다른 결손·복원 신뢰도를 집계 단계에서 차등 가중하는 것이다.

🔬 기술적 접근법

📊 주요 결과

💭 의의 및 한계

**의의**: 모달리티 결손과 데이터 격리가 함께 발생하는 실세계 멀티 파티 그래프 환경(의료·금융·소셜)에 적용 가능한 강건한 연합 학습 청사진을 제공. **한계**: 3 태스크·6 데이터셋이라는 평가 범위로, 매우 큰 그래프나 다양한 모달리티 조합(예: 비디오·시계열)에서의 확장성은 추가 검증 필요.

🚀 실용적 활용