# Multimodal Deep Network Embedding with Integrated Structure and Attribute Information

arXiv: https://arxiv.org/abs/1903.12019 · HTML: https://mlsanity.com/paper/1903.12019/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Mar 2019.

## Built on by (most cited first, 4 of 4)

- [Multiscale Spatio-Temporal Graph Neural Networks for 3D Skeleton-Based Motion Prediction](https://mlsanity.com/paper/2108.11244/) (2021)
- [Skeleton-Parted Graph Scattering Networks for 3D Human Motion Prediction](https://mlsanity.com/paper/2208.00368/) (2022)
- [Deep Attributed Network Representation Learning via Attribute Enhanced Neighborhood](https://mlsanity.com/paper/2104.05234/) (2021)
- [Network Representation Learning for Biophysical Neural Network Analysis](https://mlsanity.com/paper/2410.11503/) (2024)

## Abstract (arXiv)

Network embedding is the process of learning low-dimensional representations for nodes in a network, while preserving node features. Existing studies only leverage network structure information and focus on preserving structural features. However, nodes in real-world networks often have a rich set of attributes providing extra semantic information. It has been demonstrated that both structural and attribute features are important for network analysis tasks. To preserve both features, we investigate the problem of integrating structure and attribute information to perform network embedding and propose a Multimodal Deep Network Embedding (MDNE) method. MDNE captures the non-linear network structures and the complex interactions among structures and attributes, using a deep model consisting of multiple layers of non-linear functions. Since structures and attributes are two different types of information, a multimodal learning method is adopted to pre-process them and help the model to better capture the correlations between node structure and attribute information. We employ both structural proximity and attribute proximity in the loss function to preserve the respective features and the representations are obtained by minimizing the loss function. Results of extensive experiments on four real-world datasets show that the proposed method performs significantly better than baselines on a variety of tasks, which demonstrate the effectiveness and generality of our method.