CAMPA: Efficient and Aligned Multimodal Graph Learning via Decoupled Propagation and Aggregation

• URL: http://arxiv.org/abs/2605.11468v1
• Date: Tue, 12 May 2026 03:32:54 GMT
• Title: CAMPA: Efficient and Aligned Multimodal Graph Learning via Decoupled Propagation and Aggregation
• Abstract summary: Multimodal Graph Neural Networks (MGNNs) have shown strong potential for learning from multimodal attributed graphs.<n>Most existing approaches rely on tightly coupled architectures that suffer from prohibitive computational overhead.<n>We present a systematic empirical analysis showing that decoupled MGNNs are substantially more efficient and scalable for large-scale graph learning.
• Score: 37.04773834936237
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multimodal Graph Neural Networks (MGNNs) have shown strong potential for learning from multimodal attributed graphs, yet most existing approaches rely on tightly coupled architectures that suffer from prohibitive computational overhead. In this paper, we present a systematic empirical analysis showing that decoupled MGNNs are substantially more efficient and scalable for large-scale graph learning. However, we identify a critical bottleneck in existing decoupled pipelines, namely modal conflict, which arises in both the propagation and aggregation stages. Specifically, independent multi-hop diffusion causes cross-modal semantic divergence during propagation, while naive fusion fails to align multi-hop feature trajectories during aggregation, jointly limiting effective representation learning. To address this challenge, we propose CAMPA, a Cross-modal Aligned Multimodal Propagation & Aggregation framework for decoupled multimodal graph learning. Concretely, CAMPA introduces a two-stage alignment mechanism: (1) cross-modal aligned propagation, which injects cross-modal similarity priors into message passing to preserve semantic consistency without additional parameter overhead; (2) trajectory aligned aggregation, which leverages trajectory-level self-attention and cross-attention to capture and align long-range dependencies across modalities and hops. Extensive experiments on diverse benchmark datasets and tasks demonstrate that CAMPA consistently outperforms strong coupled and decoupled baselines while preserving the efficiency advantages of the decoupled paradigm.

Related papers

• ReCoG: Reciprocal Co-Evolution for Multimodal Graph Learning [9.030717765733398]
  Multimodal graph learning requires jointly training over graph structure and heterogeneous node attributes.<n>We propose ReCoG, a new learning paradigm that tightly couples graph structure learning and multimodal representation learning.<n>Our results demonstrate that reciprocal co-evolution of structure and semantics is important for effective multimodal graph learning.
  arXiv  Detail & Related papers  (2026-08-24T04:16:13Z)
• 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)
• PivotMerge: Bridging Heterogeneous Multimodal Pre-training via Post-Alignment Model Merging [80.17966517536102]
  We argue that the core of Multimodal Large Language Models pre-training lies in establishing effective cross-modal alignment.<n>Motivated by this insight, we introduce the post-alignment merging task, which aims to integrate cross-modal alignment capabilities learned from multimodal pre-training.<n>We propose PivotMerge, a post-alignment merging framework for cross-modal projectors.
  arXiv  Detail & Related papers  (2026-04-18T09:38:03Z)
• AlignMamba-2: Enhancing Multimodal Fusion and Sentiment Analysis with Modality-Aware Mamba [56.52470564147458]
  We propose textbfAlignMamba-2, an effective and efficient framework for multimodal fusion and sentiment analysis.<n>Our approach introduces a dual alignment strategy that regularizes the model using both Optimal Transport distance and Maximum Mean Discrepancy.<n>More importantly, we design a Modality-Aware Mamba layer, which employs a Mixture-of-Experts architecture with modality-specific and modality-shared experts.
  arXiv  Detail & Related papers  (2026-03-19T03:47:21Z)
• Multimodal Graph Representation Learning with Dynamic Information Pathways [12.019248723233673]
  We propose a novel multimodal graph representation learning framework with Dynamic information Pathways (DiP)<n>DiP enables dynamic message routing within each modality via proximity-guided pseudo-node interactions.<n>Experiments across multiple benchmarks demonstrate that DiP consistently outperforms baselines.
  arXiv  Detail & Related papers  (2026-03-10T06:45:59Z)
• Toward Effective Multimodal Graph Foundation Model: A Divide-and-Conquer Based Approach [42.970648490410504]
  Multimodal Graph Foundation Models (MGFMs) allow for leveraging the rich multimodal information in Multimodal-Attributed Graphs (MAGs)<n>We propose PLANET, a novel framework employing a Divide-and-Conquer strategy to decouple modality interaction and alignment across distinct granularities.<n>We show that PLANET significantly outperforms state-of-the-art baselines across diverse graph-centric and multimodal generative tasks.
  arXiv  Detail & Related papers  (2026-02-04T01:05:12Z)
• Cross-Modal Attention Network with Dual Graph Learning in Multimodal Recommendation [12.802844514133255]
  Cross-modal Recursive Attention Network with dual graph Embedding (CRANE)<n>We design a core Recursive Cross-Modal Attention (RCA) mechanism that iteratively refines modality features based on cross-correlations in a joint latent space.<n>For symmetric multimodal learning, we explicitly construct users' multimodal profiles by aggregating features of their interacted items.
  arXiv  Detail & Related papers  (2026-01-16T10:09:39Z)
• Amplifying Prominent Representations in Multimodal Learning via Variational Dirichlet Process [55.91649771370862]
  Dirichlet process (DP) mixture model is a powerful non-parametric method that can amplify the most prominent features.<n>We propose a new DP-driven multimodal learning framework that automatically achieves an optimal balance between prominent intra-modal representation learning and cross-modal alignment.
  arXiv  Detail & Related papers  (2025-10-23T16:53:24Z)
• Explaining multimodal LLMs via intra-modal token interactions [55.27436637894534]
  Multimodal Large Language Models (MLLMs) have achieved remarkable success across diverse vision-language tasks, yet their internal decision-making mechanisms remain insufficiently understood.<n>We propose enhancing interpretability by leveraging intra-modal interaction.
  arXiv  Detail & Related papers  (2025-09-26T14:39:13Z)
• MoCa: Modality-aware Continual Pre-training Makes Better Bidirectional Multimodal Embeddings [75.0617088717528]
  MoCa is a framework for transforming pre-trained VLM backbones into effective bidirectional embedding models.<n>MoCa consistently improves performance across MMEB and ViDoRe-v2 benchmarks, achieving new state-of-the-art results.
  arXiv  Detail & Related papers  (2025-06-29T06:41:00Z)
• GeoMM: On Geodesic Perspective for Multi-modal Learning [55.41612200877861]
  This paper introduces geodesic distance as a novel distance metric in multi-modal learning for the first time.<n>Our approach incorporates a comprehensive series of strategies to adapt geodesic distance for the current multimodal learning.
  arXiv  Detail & Related papers  (2025-05-16T13:12:41Z)
• Fast Disentangled Slim Tensor Learning for Multi-view Clustering [28.950845031752927]
  We propose a new approach termed fast Disdentangle Slim Learning (DSTL) for multi-view clustering. To alleviate the negative influence of feature redundancy, inspired by robust PCA, DSTL disentangles the latent low-dimensional representation into a semantic-unrelated part and a semantic-related part for each view. Our proposed model is computationally efficient and can be solved effectively.
  arXiv  Detail & Related papers  (2024-11-12T09:57:53Z)
• Joint Demand Prediction for Multimodal Systems: A Multi-task Multi-relational Spatiotemporal Graph Neural Network Approach [7.481812882780837]
  This study proposes a multi-relational graph neural network (MRGNN) for multimodal demand prediction. A multi-relational graph neural network (MRGNN) is introduced to capture cross-mode heterogeneous spatial dependencies. Experiments are conducted using real-world datasets from New York City.
  arXiv  Detail & Related papers  (2021-12-15T12:35:35Z)

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.