FedGAMMA is proposed, casting federated multimodal graph foundation learning as a two-stage semantic-structural alignment problem of federated pre-training and prompt-based fine-tuning, and outperforms competitive baselines accross multi-domain datasets on multiple tasks.
Abstract
Multimodal-attributed graphs (MAGs), whose nodes carry modalities such as images and text alongside topological structure, now pervade applications including social platforms, e-commerce, and biomedical networks, offering richer semantic signals than single-modality graphs. In practice, such graphs are fragmented across privacy-restricted silos owned by different platforms and institutions, so learning a broadly transferable model over them demands collaborative training that never exposes raw data. This places the task at the intersection of multimodal graph learning and federated learning, yet existing methods cover only one side of it. To address the challenges from these two perspectives, we propose FedGAMMA, casting federated multimodal graph foundation learning as a two-stage semantic-structural alignment problem of federated pre-training and prompt-based fine-tuning. During pre-training, a shared-private semantic enhancer disentangles cross-modal commonality from modality-specific information, aligning it through optimal transport, a topology-aware graph fusion module decouples semantic and structural views via semantic residual graphs and dual positional encodings, and a dual-channel affinity-aware aggregation mechanism estimates client similarity from feature and graph centroids without exposing raw data. During fine-tuning, FedGAMMA adapts the pretrained encoder through lightweight graph-aware prompts, a shared prompt pool with controlled exploration, and channel-wise prompt synchronization. Experiments on twelve multimodal graph datasets show FedGAMMA consistently surpassing a broad range of baselines across downstream tasks, with gains of up to 12.96%. FedGAMMA further outperforms competitive baselines accross multi-domain datasets on multiple tasks with up to 5.71% under few-shot learning scenario.
Multimodal-attributed graphs (MAGs), where nodes carry heterogeneous semantic content across multiple modalities while edges encode relational dependencies, have been widely adopted across diverse domains. Federated multimodal graph learning (FMGL) extends federated graph learning (FGL) to MAGs, enabling collaborative optimization across decentralized MAGs without exposing raw data. However, naively applying existing FGL methods to FMGL is insufficient, as they fail to navigate the multifaceted heterogeneity inherent in decentralized MAGs, including task heterogeneity across diverse client objectives, modality heterogeneity from discrepant modality quality and semantic domains, and topology heterogeneity arising from divergent topological patterns with low cross-modality correlation. To address these challenges, we propose Federated multimodal graph learning with Topology-aware Cross-modal Routing (FedTCR), the first systematic algorithm designed for FMGL. To handle task heterogeneity, FedTCR employs a two-stage paradigm that comprises federated task-agnostic pre-training followed by isolated task-oriented fine-tuning. To jointly address modality and topology heterogeneity, FedTCR introduces a topology-aware cross-modal routing mechanism. Concretely, each client distills modality-specific knowledge into compact prototypes via topology-aware importance-weighted aggregation informed by graph structure; the server then evaluates cross-client cross-modal relationships among these structure-informed prototypes and routes informative ones as contrastive references, driving a tri-level cross-modal contrastive learning scheme that jointly aligns cross-client modalities while preserving discrimination. Experiments across 7 domains demonstrate that FedTCR outperforms state-of-the-art baselines on both graph-centric and modality-centric tasks.
A multimodal federated graph unlearning framework built around target-specific representation decoupling that effectively removes requested information, preserves retained graph utility, and achieves a speedup over full retraining.
Haodong Lu, Zekai Chen, Weiwei Ji et al.· 0 citations
ReCoG (Reciprocal Co-Evolution for Multimodal Graph Learning) is proposed, a new learning paradigm that tightly couples graph structure learning and multimodal representation learning through end-to-end reciprocal interaction and yields greater expressiveness than decoupled or two-stage formulations.
Multimodal recommendation benefits from leveraging rich content signals such as images and texts to alleviate interaction sparsity, yet existing graph-based approaches are still hindered by (i) noisy user—item edges that are treated as static during training and (ii) inconsistent representation spaces across interaction-driven and modality-induced graph views. To address these issues, we propose DIGEST, a multi-graph framework that propagates trainable ID embeddings on a denoised user—item graph and a fused modality-induced item—item graph, and interleaves message passing with dynamic graph refinement that iteratively reweights existing edges to suppress noisy connections. To enable reliable semantic transfer across views, DIGEST further introduces a dual contrastive alignment that (i) aligns the collaborative and semantic item views and (ii) constrains the semantic graph representations to projected multimodal features, together with a lightweight dimension decorrelation regularizer and adaptive gated fusion to reduce redundancy and stabilize multi-view learning. Extensive experiments on three Amazon benchmark datasets demonstrate that DIGEST consistently outperforms state-of-the-art multimodal recommenders, achieving up to 8.43% relative improvement on NDCG@20 and 7.66% on Recall@20 over the strongest baselines.
Xiangyu Sai, M. Madadi, Sergio Escalera et al.· Annual International ACM SIG...· 0 citations
Graph foundation models (GFMs) have emerged as a promising paradigm for transferring knowledge across graph domains and tasks. Real-world graphs associate nodes with text, images, and other modalities, making multimodal graphs essential for representing complex entities and relations. Moreover, collecting labels and adapting models for every new graph domain is costly and often infeasible, motivating zero-shot transfer. Unfortunately, zero-shot transfer on multimodal graphs remains underexplored. Existing GNN-based graph foundation models typically require downstream adaptation, whereas LLM-based graph methods mainly address unimodal graphs or tasks within a single domain. This setting presents two key challenges. First, models must generalize knowledge from individual modalities while capturing transferable cross-modal relations. Second, without target-domain fine-tuning, node representations remain entangled with domain-specific structures and modality-specific characteristics, obscuring shared concepts in unseen domains. To address these challenges, we propose CHARM, a multimodal graph foundation model with hierarchical context modeling for zero-shot transfer. CHARM replaces isolated raw nodes with hierarchical graph contexts that capture multimodal semantics and cross-modal relations. These contexts map domain-specific node patterns to shared high-level concepts, reducing reliance on target-domain supervision or adaptation. A modality-aware graph context encoder integrates multimodal information with graph structure and converts the resulting representations into graph tokens for a large language model . Experiments show consistent improvements on zero-shot multimodal graph tasks.
Ankang Yang, Jitao Zhao, Di Jin et al.· arXiv.org· 0 citations
The entity alignment task in Multi modal Knowledge Graph (MKG) faces challenges such as strong modal heterogeneity, large semantic gap, and inflexible fusion strategies. Existing methods generally rely on static weighted fusion and large amounts of annotated data, making it difficult to cope with complex multimodal environments. This article proposes a novel multimodal entity alignment model- TextFusionEA, which implements structural embedding based on GraphSAGE, uses MobileNetV3 to obtain visual features, introduces an adaptive fusion mechanism of semantic, structural, and visual features, and designs a semi supervised iterative learning strategy to extend the seed subset to alleviate the problem of data scarcity. Experiments on five datasets have shown that TextFusionEA performs well in MRR Hits@1. It significantly outperforms existing mainstream methods in terms of metrics, verifying its alignment performance and robustness in complex multimodal scenarios.
