STAGE: Tackling Semantic Drift in Multimodal Federated Graph Learning

• URL: http://arxiv.org/abs/2605.11919v1
• Date: Tue, 12 May 2026 10:35:43 GMT
• Title: STAGE: Tackling Semantic Drift in Multimodal Federated Graph Learning
• Abstract summary: Federated graph learning (FGL) enables collaborative training on graph data across multiple clients.<n>The key challenge is that clients from different modality domains may not share a common semantic space.<n>We propose textbfSTAGE, a protocol-first framework for MM-FGL.
• Score: 48.96526409527749
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: 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.

Related papers

• Towards Effective Federated Multimodal Graph Learning via Navigating Multifaceted Heterogeneity [12.526349151730921]
  We propose Federated multimodal graph learning with Topology-aware Cross-modal Routing (FedTCR)<n>FedTCR employs a two-stage paradigm that comprises federated task-agnostic pre-training followed by isolated task-oriented fine-tuning.<n> Experiments across 7 domains demonstrate that FedTCR outperforms state-of-the-art baselines on both graph-centric and modality-centric tasks.
  arXiv  Detail & Related papers  (2026-08-01T12:29:38Z)
• Toward Federated Multimodal Graph Foundation Models: A Topology-Aware Multimodal Alignment Framework [35.35423006939282]
  FedGAMMA casts federated multimodal graph foundation learning as a two-stage semantic-structural alignment problem.<n>During pre-training, a shared-private semantic enhancer disentangles cross-modal commonality from modality-specific information.<n>During fine-tuning, FedGAMMA adapts the pretrained encoder through lightweight graph-aware prompts.
  arXiv  Detail & Related papers  (2026-07-17T06:57:41Z)
• PRISM: Topology-Aware Cross-Modal Imputation for Modality-Deficient Federated Graph Learning [54.55726437469762]
  We propose textbfPRISM (textbfProactive textbfRetrieval and textbfImputation via textbfStructural textbfMeta-prompting), a topology-aware cross-modal imputation framework.<n>Experiments show PRISM consistently improves modality-deficient clients, outperforming state-of-the-art baselines by textbf4.48% on average.
  arXiv  Detail & Related papers  (2026-06-08T10:08:52Z)
• Rethinking Federated Graph Foundation Models: A Graph-Language Alignment-based Approach [8.517604507672262]
  Recent studies of federated graph foundational models (FedGFMs) break the idealized and untenable assumption of having centralized data storage to train graph foundation models.<n>Existing studies that project aligned generalizable knowledge onto a discrete token space via vector-quantized backbones suffer from irreversible knowledge loss during the quantization process.
  arXiv  Detail & Related papers  (2026-01-29T07:50:00Z)
• Semantic Refinement with LLMs for Graph Representations [37.72134125261354]
  We propose a Data-Adaptive Semantic Refinement framework DAS for graph representation learning.<n>We evaluate our approach on both text-rich and text-free graphs.<n>Results show consistent improvements on structure-dominated graphs while remaining competitive on semantics-rich graphs.
  arXiv  Detail & Related papers  (2025-12-24T11:10:28Z)
• GILT: An LLM-Free, Tuning-Free Graph Foundational Model for In-Context Learning [50.40400074353263]
  Graph Neural Networks (GNNs) are powerful tools for precessing relational data but often struggle to generalize to unseen graphs.<n>We introduce textbfGraph textbfIn-context textbfL textbfTransformer (GILT), a framework built on an LLM-free and tuning-free architecture.
  arXiv  Detail & Related papers  (2025-10-06T08:09:15Z)
• Rethinking Federated Graph Learning: A Data Condensation Perspective [4.044673636393338]
  Federated graph learning (FGL) promotes collaborative training of graph neural networks (GNNs) by multi-client graphs.<n>We introduce the concept of a condensed graph as a novel optimization carrier to address FGL data heterogeneity.<n>Specifically, we utilize a generalized condensation graph consensus to aggregate comprehensive knowledge from distributed graphs.
  arXiv  Detail & Related papers  (2025-05-05T11:23:29Z)
• LLM as GNN: Graph Vocabulary Learning for Text-Attributed Graph Foundation Models [87.68057302738457]
  Text-Attributed Graphs (TAGs) are ubiquitous in real-world scenarios.<n>Despite large efforts to integrate Large Language Models (LLMs) and Graph Neural Networks (GNNs) for TAGs, existing approaches suffer from decoupled architectures.<n>We propose PromptGFM, a versatile GFM for TAGs grounded in graph vocabulary learning.
  arXiv  Detail & Related papers  (2025-03-05T09:45:22Z)
• Against Multifaceted Graph Heterogeneity via Asymmetric Federated Prompt Learning [5.813912301780917]
  We propose a Federated Graph Prompt Learning (FedGPL) framework to efficiently enable prompt-based asymmetric graph knowledge transfer. We conduct theoretical analyses and extensive experiments to demonstrate the significant accuracy and efficiency effectiveness of FedGPL.
  arXiv  Detail & Related papers  (2024-11-04T11:42:25Z)
• A Pure Transformer Pretraining Framework on Text-attributed Graphs [50.833130854272774]
  We introduce a feature-centric pretraining perspective by treating graph structure as a prior. Our framework, Graph Sequence Pretraining with Transformer (GSPT), samples node contexts through random walks. GSPT can be easily adapted to both node classification and link prediction, demonstrating promising empirical success on various datasets.
  arXiv  Detail & Related papers  (2024-06-19T22:30:08Z)
• GraphMETRO: Mitigating Complex Graph Distribution Shifts via Mixture of Aligned Experts [75.51612253852002]
  GraphMETRO is a Graph Neural Network architecture that models natural diversity and captures complex distributional shifts. GraphMETRO achieves state-of-the-art results on four datasets from the GOOD benchmark.
  arXiv  Detail & Related papers  (2023-12-07T20:56:07Z)
• You Only Transfer What You Share: Intersection-Induced Graph Transfer Learning for Link Prediction [79.15394378571132]
  We investigate a previously overlooked phenomenon: in many cases, a densely connected, complementary graph can be found for the original graph. The denser graph may share nodes with the original graph, which offers a natural bridge for transferring selective, meaningful knowledge. We identify this setting as Graph Intersection-induced Transfer Learning (GITL), which is motivated by practical applications in e-commerce or academic co-authorship predictions.
  arXiv  Detail & Related papers  (2023-02-27T22:56:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.