Entity alignment refers to matching entities with the same realistic meaning in different knowledge graphs. The structure of a knowledge graph provides the global signal for entity alignment. But in the real world, a knowledge graph provides insufficient structural information in general. Moreover, the problem of knowledge graph heterogeneity is common. The semantic and string information can alleviate the problems caused by the sparse and heterogeneous nature of knowledge graphs, yet both of them have not been fully utilized by most existing work. Therefore, we propose an entity alignment model based on multiple information (EAMI), which employs structural, semantic and string information. EAMI learns the structural representation of a knowledge graph by using multi-layer graph convolutional networks. To acquire more accurate entity vector representation, we incorporate the attribute semantic representation into the structural representation. In addition, to further improve entity alignment, we study the entity name string information. There is no training required to calculate the similarity of entity names. Our model is tested on publicly available cross-lingual datasets and cross-resource datasets, and the experimental results demonstrate the effectiveness of our model.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.neunet.2023.02.029 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
A Survey of Deep Anomaly Detection in Multivariate Time Series: Taxonomy, Applications, and Directions.
Sensors (Basel)
January 2025
School of Computer Science, South China Normal University, Guangzhou 510555, China.
Multivariate time series anomaly detection (MTSAD) can effectively identify and analyze anomalous behavior in complex systems, which is particularly important in fields such as financial monitoring, industrial equipment fault detection, and cybersecurity. MTSAD requires simultaneously analyze temporal dependencies and inter-variable relationships have prompted researchers to develop specialized deep learning models to detect anomalous patterns. In this paper, we conducted a structured and comprehensive overview of the latest techniques in deep learning for multivariate time series anomaly detection methods.
View Article and Find Full Text PDFGeneration of Rational Drug-like Molecular Structures Through a Multiple-Objective Reinforcement Learning Framework.
Molecules
December 2024
Department of Medicinal Chemistry, School of Pharmacy, Fudan University, 826 Zhangheng Road, Shanghai 201203, China.
As an appealing approach for discovering novel leads, the key advantage of de novo drug design lies in its ability to explore a much broader dimension of chemical space, without being confined to the knowledge of existing compounds. So far, many generative models have been described in the literature, which have completely redefined the concept of de novo drug design. However, many of them lack practical value for real-world drug discovery.
View Article and Find Full Text PDFUncertainty modeling for inductive knowledge graph embedding.
Neural Netw
January 2025
College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, 518060, China; Guangdong Key Laboratory of Intelligent Information Processing, Shenzhen University, Shenzhen, 518060, China. Electronic address:
Article Synopsis
- In refining Knowledge Graphs, new entities appear and old ones change, leading to a problem of distribution shift for entity features during representation learning.
- Most current methods for embedding these graphs mainly focus on new entities and overlook the issues caused by this distribution shift.
- The proposed model, EDSU, uses mean and variance reconstruction to address this shift by integrating both the characteristics of entity embeddings and their neighborhood structures, resulting in improved performance in inductive link prediction tasks compared to existing models.
Altered Connectome Topology in Newborns at Risk for Cognitive Developmental Delay: A Cross-Etiologic Study.
Hum Brain Mapp
January 2025
Center for MR Research, University Children's Hospital Zurich, Zurich, Switzerland.
The human brain connectome is characterized by the duality of highly modular structure and efficient integration, supporting information processing. Newborns with congenital heart disease (CHD), prematurity, or spina bifida aperta (SBA) constitute a population at risk for altered brain development and developmental delay (DD). We hypothesize that, independent of etiology, alterations of connectomic organization reflect neural circuitry impairments in cognitive DD.
View Article and Find Full Text PDFA review of research progress in the design history of everyday life.
Heliyon
January 2025
Tongji University, College of Design and Innovation, Shanghai, China.
The study of everyday life has garnered significant research attention in various disciplines. However, in the field of design history, the exploration of everyday life remains in its early stages. There is a need for further organization and analysis, as there is currently no comprehensive exposition on the overall research progress in this field.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!