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

arXiv: https://arxiv.org/abs/2605.11468 · HTML: https://mlsanity.com/paper/2605.11468/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 46 references that are in the map.
- First posted on arXiv 12 May 2026.

## Builds on (most cited first, 30 of 32)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [Simplifying Graph Convolutional Networks](https://mlsanity.com/paper/1902.07153/) (2019)
- [Simple and Deep Graph Convolutional Networks](https://mlsanity.com/paper/2007.02133/) (2020)
- [How Attentive are Graph Attention Networks?](https://mlsanity.com/paper/2105.14491/) (2021)
- [SIGN: Scalable Inception Graph Neural Networks](https://mlsanity.com/paper/2004.11198/) (2020)
- [RedCaps: web-curated image-text data created by the people, for the people](https://mlsanity.com/paper/2111.11431/) (2021)
- [Rumor Detection on Social Media with Bi-Directional Graph Convolutional Networks](https://mlsanity.com/paper/2001.06362/) (2020)
- [NAGphormer: A Tokenized Graph Transformer for Node Classification in Large Graphs](https://mlsanity.com/paper/2206.04910/) (2022)
- [Graph Attention Multi-Layer Perceptron](https://mlsanity.com/paper/2206.04355/) (2022)
- [Fine-Grained Spoiler Detection from Large-Scale Review Corpora](https://mlsanity.com/paper/1905.13416/) (2019)
- [How to Read Paintings: Semantic Art Understanding with Multi-Modal Retrieval](https://mlsanity.com/paper/1810.09617/) (2018)
- [UniGraph2: Learning a Unified Embedding Space to Bind Multimodal Graphs](https://mlsanity.com/paper/2502.00806/) (2025)
- [Graph Neural Networks: Taxonomy, Advances and Trends](https://mlsanity.com/paper/2012.08752/) (2020)
- [Node Dependent Local Smoothing for Scalable Graph Learning](https://mlsanity.com/paper/2110.14377/) (2021)
- [LGMRec: Local and Global Graph Learning for Multimodal Recommendation](https://mlsanity.com/paper/2312.16400/) (2023)
- [Mosaic of Modalities: A Comprehensive Benchmark for Multimodal Graph Learning](https://mlsanity.com/paper/2406.16321/) (2024)
- [Multimodal Graph Learning for Generative Tasks](https://mlsanity.com/paper/2310.07478/) (2023)
- [When Graph meets Multimodal: Benchmarking and Meditating on Multimodal Attributed Graphs Learning](https://mlsanity.com/paper/2410.09132/) (2024)
- [GRAPHGPT-O: Synergistic Multimodal Comprehension and Generation on Graphs](https://mlsanity.com/paper/2502.11925/) (2025)
- [Graph4MM: Weaving Multimodal Learning with Structural Information](https://mlsanity.com/paper/2510.16990/) (2025)
- [InstructG2I: Synthesizing Images from Multimodal Attributed Graphs](https://mlsanity.com/paper/2410.07157/) (2024)
- [Cross-Contrastive Clustering for Multimodal Attributed Graphs with Dual Graph Filtering](https://mlsanity.com/paper/2511.20030/) (2025)
- [OpenMAG: A Comprehensive Benchmark for Multimodal-Attributed Graph](https://mlsanity.com/paper/2602.05576/) (2026)
- [MLaGA: Multimodal Large Language and Graph Assistant](https://mlsanity.com/paper/2506.02568/) (2025)
- [MGDCF: Distance Learning via Markov Graph Diffusion for Neural Collaborative Filtering](https://mlsanity.com/paper/2204.02338/) (2022)

## Built on by (most cited first, 2 of 2)

- [Toward Federated Multimodal Graph Foundation Models: A Topology-Aware Multimodal Alignment Framework](https://mlsanity.com/paper/2607.15687/) (2026)
- [GOMA: Toward Structure-Driven Multimodal Alignment from a Graph Signal Smoothing Perspective](https://mlsanity.com/paper/2605.15723/) (2026)

## Abstract (arXiv)

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.