paper-with-me

홈 › Papers

STAGE: Tackling Semantic Drift in Multimodal Federated Graph Learning

2026-05-12 · Zekai Chen, Xun Wu, Xunkai Li, Yihan Sun, Rong-Hua Li, Guoren Wang arxiv

Federated graph learning (FGL) enables collaborative training on graph data across multiple clients. As graph data increasingly contain multimodal node attributes such as text and images, multimodal federated graph learning (MM-FGL) has become an important yet substantially harder setting. The key challenge is that clients from different modality domains may not share a common semantic space: even for the same concept, their local encoders can produce inconsistent representations before collaboration begins. This makes direct parameter coordination unreliable and further causes two downstream problems: forcing heterogeneous client representations into a naively shared semantic space may create false semantic agreement, and graph message passing may amplify residual inconsistency across neighborhoods. To address this issue, we propose \textbf{STAGE}, a protocol-first framework for MM-FGL. Instead of relying on direct parameter averaging, STAGE builds a shared semantic space that first translates heterogeneous multimodal features into comparable representations and then regulates how these representations propagate over local graph structures. In this way, STAGE not only improves cross-client semantic calibration, but also reduces the risk of inconsistency amplification during graph learning. Extensive experiments on 8 multimodal-attributed graphs across 5 graph-centric and modality-centric tasks show that STAGE consistently achieves state-of-the-art performance while reducing per-round communication payload.

📄 PDF Abstract BibTeX arXiv:2605.11919

Code (0)

등록된 구현이 없습니다.

Tasks

Graph Learning

Similar Papers 제목 키워드 기반

Classifier Clustering and Feature Alignment for Federated Learning under Distributed Concept Drift

2024-10-24 · Junbao Chen, Jingfeng Xue, Yong Wang, Zhenyan Liu 외

Data heterogeneity is one of the key challenges in federated learning, and many efforts have been devoted to tackling this problem. However, distributed concept drift with data heterogeneity, where clients may additional…

ClusteringFederated Learning

FedFrozen: Two-Stage Federated Optimization via Attention Kernel Freezing

2026-05-07 · Junye Du, Zhenghao Li, Yushi Feng, Long Feng arxiv

Federated learning with heterogeneous clients remains a significant challenge for deep learning, primarily due to client drift arising from inconsistent local updates. Existing federated optimization methods typically ad…

Federated Learning

Concept Drift Detection in Federated Networked Systems

2021-09-13 · Dimitrios Michael Manias, Ibrahim Shaer, Li Yang, Abdallah Shami

As next-generation networks materialize, increasing levels of intelligence are required. Federated Learning has been identified as a key enabling technology of intelligent and distributed networks; however, it is prone t…

Dimensionality ReductionDrift DetectionFederated Learning

AlignFed: Alignment-Aware Asynchronous Federated Fine-Tuning for Large Language Models in Heterogeneous Edge Environments

2026-06-06 · Yan Wang, Ziyi Gao, Rui Wang arxiv

Large Language Models (LLMs) have significantly propelled the advancement of edge intelligence and have been widely deployed across various scenarios, including autonomous driving, industrial inspection, and personalized…

Federated LearningAutonomous Driving

FedTaste: Topology-Aware Structural Transfer for Multimodal Federated Learning with Missing Modalities

2026-07-25 · Haochen Liang, Jie Zhang, Hideya Ochiai arxiv

Multimodal Federated Learning is often challenged by arbitrary modality missingness and Non-IID data distributions, which lead to severe representation drift and hinder effective collaboration across clients. Existing me…

Federated Learning