Fusing heterogeneous information for multi-modal attributed network embedding

In the real world, networks with many types of nodes and edges are complex, forming a heterogeneous network. For instance, film networks contain different node types, such as directors, films and actors, as well as different types of edge and multimodal attributes. Most existing attribution network...

Full description

Saved in:
Bibliographic Details
Published in:Applied intelligence (Dordrecht, Netherlands) Netherlands), 2023-10, Vol.53 (19), p.22328-22347
Main Authors: Jieyi, Yang, Feng, Zhu, Yihong, Dong, Jiangbo, Qian
Format: Article
Language:English
Subjects:
Algorithms
Artificial Intelligence
Computer Science
Data integration
Datasets
Design
Embedding
Graph representations
Heterogeneity
Information sources
Learning
Machine learning
Machines
Manufacturing
Mechanical Engineering
Motion picture directors & producers
Networks
Performance evaluation
Processes
Representations
Semantics
Teaching methods
Topology
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In the real world, networks with many types of nodes and edges are complex, forming a heterogeneous network. For instance, film networks contain different node types, such as directors, films and actors, as well as different types of edge and multimodal attributes. Most existing attribution network embedding algorithms cannot flexibly capture the impact of multimodal attributes on the topology. Premature fusion of multimodal features encodes different attribute information into the representation embedding, while the later fusion strategy ignores the interaction between different modes, both of which affect the modeling of graph embedding.To solve this problem, we propose a multimodal attribute network representation learning algorithm based on heterogeneity information fusion, named FHIANE. It extracts features from multimodal information sources through deep heterogeneous convolutional networks and projects them into a consistent semantic space while maintaining structural information. In addition, we design a modality fusion network based on an extended attention mechanism that takes full advantage of the consistency and complementarity of multimodal information. We evaluate the performance of the FHIANE algorithm on several real datasets through challenging tasks such as link prediction and node classification. The experimental results show that FHIANE outperforms other baselines.
ISSN:0924-669X
1573-7497
DOI:10.1007/s10489-023-04675-5