NSTL国家科技图书文献中心

1. Unaligned Federated Knowledge Graph Embedding NSTL国家科技图书文献中心

Deyu Chen | Hong Zhu ... - 《The Semantic Web - ISWC 2024,Part I》 - International Semantic Web Conference - 2025, - 180～198 - 共19页

摘要：Recently, knowledge graph* embedding (KGE* | ) methods under the federated learning paradigm have | received much attention. Its privacy-preserving | decentralized training method effectively utilizes the | knowledge graphs held by different clients. Existing

关键词： Knowledge graph embedding | Federated learning | Heterogeneous data

2. Zero-Shot Heterogeneous Graph Embedding via Semantic Extraction NSTL国家科技图书文献中心

Zhichao Luo | Siyuan Zhao ... - 《PRICAI 2024,Part II》 - Pacific Rim International Conference on Artificial Intelligence - 2025, - 29～41 - 共13页

摘要：Graph embedding, which aims to project a graph | significant attention. Semi-supervised graph* embedding takes* | formidable challenge for conventional graph embedding | novel heterogeneous graph* embedding method, termed* | Semantic Heterogeneous Graph* Convolutional Network (SHGCN*

关键词： Graph embedding | Graph neural network | Zero-shot learning

3. Dissimilarity-Based Graph Embedding: An Efficient GAT-based Approach NSTL国家科技图书文献中心

Francesco Leonardi | Kaspar Riesen - 《Pattern Recognition,Part X》 - International Conference on Pattern Recognition - 2025, - 361～374 - 共14页

摘要：Graph embedding into vector spaces is a widely | . Several methods for graph* embedding have been proposed* | Dissimilarity Based Graph* Embedding (DBGE) for the first time* | used practice in graph-based pattern recognition to | bypass the mathematical limitations of the graph* domain*

关键词： Graph embedding | Graph edit distance | Graph neural network

4. StrucGCN: Structural enhanced graph convolutional networks for graph embedding NSTL国家科技图书文献中心

Zhang, Jie | Li, Mingxuan ... - 《Information Fusion》 - 2025,117 - 共22页

摘要：In graph* embedding, many popular Graph Neural* | efficient graph learning framework based on Graph | Convolutional Networks (GCN), called structural enhanced graph | the adjacency matrix across different graph* datasets* | Networks (GNNs) rely on node features and the adjacency

关键词： Graph embedding | Graph convolutional network | Structural similarity | Homophily

5. Improving Disease Comorbidity Prediction with Biologically Supervised Graph Embedding NSTL国家科技图书文献中心

Xihan Qin | Li Liao - 《Computational Advances in Bio and Medical Sciences》 - International Conference on Computational Advances in Bio and Medical Sciences - 2025, - 178～190 - 共13页

摘要： Graph Embedding (BSE) to select the most relevant | features from the graph* embedding for disease subgraphs* | -Supervised-Graph-Embedding. | and management. In graph* machine learning, it is* | BSE's impact on both centered and uncentered embedding

关键词： Comorbidity | Human interactome | Graph embedding | Supervised embedding | Isomap

6. Federal Knowledge Graph Embedding Based on Incentive Mechanism NSTL国家科技图书文献中心

Lijun Chen | Yudong Zhang ... - 《Network and Parallel Computing,Part II》 - IFIP WG 10.3 International Conference on Network and Parallel Computing - 2025, - 153～165 - 共13页

摘要： their data. Traditional knowledge graph embedding | Currently, the task of knowledge graph | multi-source knowledge graph* data while ensuring that* | embedding in multi-source knowledge graphs and introduces | inference based on federated learning remains impractical

关键词： Knowledge graph embedding | Federated learning | Incentive mechanism

7. Decoupled semantic graph neural network for knowledge graph embedding NSTL国家科技图书文献中心

Li Z. | Xiao K.... - 《Neurocomputing》 - 2025,611(Jan.1) - 1.1～1.11 - 共11页 - 被引量：1

摘要：© 2024 Elsevier B.V.Knowledge graph embedding | (KGE) learns an embedding* space for a more accurate* | semantic graph* network for KGE (named DSGNet), which* | projecting the knowledge graph* into distinct semantic* | representation of entities and relations. Although the KGE

关键词： Graph neural network | Knowledge graph completion | Knowledge graph embedding | Knowledge graphs

8. Effective Knowledge Graph Embedding with Quaternion Convolutional Networks NSTL国家科技图书文献中心

Qiuyu Liang | Weihua Wang ... - 《Natural Language Processing and Chinese Computing,Part III》 - CCF International Conference on Natural Language Processing and Chinese Computing - 2025, - 183～196 - 共14页

摘要： demonstrated effectiveness in knowledge graph* embedding, but* | novel knowledge graph* embedding model, which utilizes* | our model on multiple knowledge graph* completion* | Convolutional Neural Networks (CNNs) have | existing CNN-based methods encounter two main challenges

关键词： Quaternion algebra | Knowledge graph embedding | Link prediction | Convolutional neural network

9. C-KGE: Curriculum learning-based Knowledge Graph Embedding NSTL国家科技图书文献中心

Diange Zhou | Shengwen Li ... - 《Computer speech & language》 - 2025,89(Jan.) - 101689.1～101689.11 - 共11页

摘要：Knowledge graph* embedding (KGE) aims to embed* | proposed model achieves improved embedding* performances* | entities and relations in knowledge graphs (KGs) into a | continuous, low-dimensional vector space. It has been shown | as an effective tool for integrating knowledge

关键词： Knowledge graph embedding | Knowledge graph | Curriculum learning | link prediction

10. A Knowledge Graph Embedding Model for Answering Factoid Entity Questions NSTL国家科技图书文献中心

PARASTOO JAFARZADEH | FAEZEH ENSAN ... - 《ACM transactions on information systems》 - 2025,43(2) - 38.1～38.27 - 共27页 - 被引量：1

摘要： article introduces the knowledge graph* embedding model* | a knowledge graph* embedding approach is utilized* | knowledge graph* derived from extensive text collections* | from the textual knowledge graph* based on semantic* | positioning the embedding* for the answer entity close to the*

摘要：Recently, knowledge graph* embedding (KGE* | ) methods under the federated learning paradigm have | received much attention. Its privacy-preserving | decentralized training method effectively utilizes the | knowledge graphs held by different clients. Existing

关键词： Knowledge graph embedding | Federated learning | Heterogeneous data

摘要：Graph embedding, which aims to project a graph | significant attention. Semi-supervised graph* embedding takes* | formidable challenge for conventional graph embedding | novel heterogeneous graph* embedding method, termed* | Semantic Heterogeneous Graph* Convolutional Network (SHGCN*

关键词： Graph embedding | Graph neural network | Zero-shot learning

摘要：Graph embedding into vector spaces is a widely | . Several methods for graph* embedding have been proposed* | Dissimilarity Based Graph* Embedding (DBGE) for the first time* | used practice in graph-based pattern recognition to | bypass the mathematical limitations of the graph* domain*

关键词： Graph embedding | Graph edit distance | Graph neural network

摘要：In graph* embedding, many popular Graph Neural* | efficient graph learning framework based on Graph | Convolutional Networks (GCN), called structural enhanced graph | the adjacency matrix across different graph* datasets* | Networks (GNNs) rely on node features and the adjacency

关键词： Graph embedding | Graph convolutional network | Structural similarity | Homophily

摘要： Graph Embedding (BSE) to select the most relevant | features from the graph* embedding for disease subgraphs* | -Supervised-Graph-Embedding. | and management. In graph* machine learning, it is* | BSE's impact on both centered and uncentered embedding

关键词： Comorbidity | Human interactome | Graph embedding | Supervised embedding | Isomap

摘要： their data. Traditional knowledge graph embedding | Currently, the task of knowledge graph | multi-source knowledge graph* data while ensuring that* | embedding in multi-source knowledge graphs and introduces | inference based on federated learning remains impractical

关键词： Knowledge graph embedding | Federated learning | Incentive mechanism

摘要：© 2024 Elsevier B.V.Knowledge graph embedding | (KGE) learns an embedding* space for a more accurate* | semantic graph* network for KGE (named DSGNet), which* | projecting the knowledge graph* into distinct semantic* | representation of entities and relations. Although the KGE

关键词： Graph neural network | Knowledge graph completion | Knowledge graph embedding | Knowledge graphs

摘要： demonstrated effectiveness in knowledge graph* embedding, but* | novel knowledge graph* embedding model, which utilizes* | our model on multiple knowledge graph* completion* | Convolutional Neural Networks (CNNs) have | existing CNN-based methods encounter two main challenges

关键词： Quaternion algebra | Knowledge graph embedding | Link prediction | Convolutional neural network

摘要：Knowledge graph* embedding (KGE) aims to embed* | proposed model achieves improved embedding* performances* | entities and relations in knowledge graphs (KGs) into a | continuous, low-dimensional vector space. It has been shown | as an effective tool for integrating knowledge

关键词： Knowledge graph embedding | Knowledge graph | Curriculum learning | link prediction

摘要： article introduces the knowledge graph* embedding model* | a knowledge graph* embedding approach is utilized* | knowledge graph* derived from extensive text collections* | from the textual knowledge graph* based on semantic* | positioning the embedding* for the answer entity close to the*

关键词： Textual knowledge graph | entity question answering | knowledge graph embedding for question answering

4008-161-200 800-990-8900

国家科技图书文献中心

摘要：Recently, knowledge graph embedding (KGE | ) methods under the federated learning paradigm have | received much attention. Its privacy-preserving | decentralized training method effectively utilizes the | knowledge graphs held by different clients. Existing

关键词： Knowledge graph embedding | Federated learning | Heterogeneous data

摘要：Graph embedding, which aims to project a graph | significant attention. Semi-supervised graph embedding takes | formidable challenge for conventional graph embedding | novel heterogeneous graph embedding method, termed | Semantic Heterogeneous Graph Convolutional Network (SHGCN

关键词： Graph embedding | Graph neural network | Zero-shot learning

摘要：Graph embedding into vector spaces is a widely | . Several methods for graph embedding have been proposed | Dissimilarity Based Graph Embedding (DBGE) for the first time | used practice in graph-based pattern recognition to | bypass the mathematical limitations of the graph domain

关键词： Graph embedding | Graph edit distance | Graph neural network

摘要：In graph embedding, many popular Graph Neural | efficient graph learning framework based on Graph | Convolutional Networks (GCN), called structural enhanced graph | the adjacency matrix across different graph datasets | Networks (GNNs) rely on node features and the adjacency

关键词： Graph embedding | Graph convolutional network | Structural similarity | Homophily

摘要： Graph Embedding (BSE) to select the most relevant | features from the graph embedding for disease subgraphs | -Supervised-Graph-Embedding. | and management. In graph machine learning, it is | BSE's impact on both centered and uncentered embedding

关键词： Comorbidity | Human interactome | Graph embedding | Supervised embedding | Isomap

摘要： their data. Traditional knowledge graph embedding | Currently, the task of knowledge graph | multi-source knowledge graph data while ensuring that | embedding in multi-source knowledge graphs and introduces | inference based on federated learning remains impractical

关键词： Knowledge graph embedding | Federated learning | Incentive mechanism

摘要：© 2024 Elsevier B.V.Knowledge graph embedding | (KGE) learns an embedding space for a more accurate | semantic graph network for KGE (named DSGNet), which | projecting the knowledge graph into distinct semantic | representation of entities and relations. Although the KGE

关键词： Graph neural network | Knowledge graph completion | Knowledge graph embedding | Knowledge graphs

摘要： demonstrated effectiveness in knowledge graph embedding, but | novel knowledge graph embedding model, which utilizes | our model on multiple knowledge graph completion | Convolutional Neural Networks (CNNs) have | existing CNN-based methods encounter two main challenges

关键词： Quaternion algebra | Knowledge graph embedding | Link prediction | Convolutional neural network

摘要：Knowledge graph embedding (KGE) aims to embed | proposed model achieves improved embedding performances | entities and relations in knowledge graphs (KGs) into a | continuous, low-dimensional vector space. It has been shown | as an effective tool for integrating knowledge

关键词： Knowledge graph embedding | Knowledge graph | Curriculum learning | link prediction

摘要： article introduces the knowledge graph embedding model | a knowledge graph embedding approach is utilized | knowledge graph derived from extensive text collections | from the textual knowledge graph based on semantic | positioning the embedding for the answer entity close to the

关键词： Textual knowledge graph | entity question answering | knowledge graph embedding for question answering

4008-161-200 800-990-8900

国家科技图书文献中心

摘要：Recently, knowledge graph* embedding (KGE* | ) methods under the federated learning paradigm have | received much attention. Its privacy-preserving | decentralized training method effectively utilizes the | knowledge graphs held by different clients. Existing

摘要：Graph embedding, which aims to project a graph | significant attention. Semi-supervised graph* embedding takes* | formidable challenge for conventional graph embedding | novel heterogeneous graph* embedding method, termed* | Semantic Heterogeneous Graph* Convolutional Network (SHGCN*

摘要：Graph embedding into vector spaces is a widely | . Several methods for graph* embedding have been proposed* | Dissimilarity Based Graph* Embedding (DBGE) for the first time* | used practice in graph-based pattern recognition to | bypass the mathematical limitations of the graph* domain*

摘要：In graph* embedding, many popular Graph Neural* | efficient graph learning framework based on Graph | Convolutional Networks (GCN), called structural enhanced graph | the adjacency matrix across different graph* datasets* | Networks (GNNs) rely on node features and the adjacency

摘要： Graph Embedding (BSE) to select the most relevant | features from the graph* embedding for disease subgraphs* | -Supervised-Graph-Embedding. | and management. In graph* machine learning, it is* | BSE's impact on both centered and uncentered embedding

摘要： their data. Traditional knowledge graph embedding | Currently, the task of knowledge graph | multi-source knowledge graph* data while ensuring that* | embedding in multi-source knowledge graphs and introduces | inference based on federated learning remains impractical

摘要：© 2024 Elsevier B.V.Knowledge graph embedding | (KGE) learns an embedding* space for a more accurate* | semantic graph* network for KGE (named DSGNet), which* | projecting the knowledge graph* into distinct semantic* | representation of entities and relations. Although the KGE

摘要： demonstrated effectiveness in knowledge graph* embedding, but* | novel knowledge graph* embedding model, which utilizes* | our model on multiple knowledge graph* completion* | Convolutional Neural Networks (CNNs) have | existing CNN-based methods encounter two main challenges

摘要：Knowledge graph* embedding (KGE) aims to embed* | proposed model achieves improved embedding* performances* | entities and relations in knowledge graphs (KGs) into a | continuous, low-dimensional vector space. It has been shown | as an effective tool for integrating knowledge

摘要： article introduces the knowledge graph* embedding model* | a knowledge graph* embedding approach is utilized* | knowledge graph* derived from extensive text collections* | from the textual knowledge graph* based on semantic* | positioning the embedding* for the answer entity close to the*