Knowledge graph representation learning with simplifying hierarchical feature propagation
School of Computer Science and Information Engineering, Hubei University, Wuhan, Hubei 430062, China
School of Information Management, Central China Normal University, Wuhan, Hubei 430072, China
Faculty of Artificial Intelligence in Education, Central China Normal University, Wuhan, Hubei 430079, China
School of Computer Science, Wuhan University, Wuhan, Hubei 430072, China
![](http://omraadeinfo.online/777/templates/cheerup1/res/banner1.gif)
New Citation Alert added!
This alert has been successfully added and will be sent to:
You will be notified whenever a record that you have chosen has been cited.
To manage your alert preferences, click on the button below.
New Citation Alert!
Please log in to your account
- Publisher Site
Information Processing and Management: an International Journal
![ACM Digital Library ACM Digital Library](https://dlnext.acm.org/specs/products/acm/releasedAssets/images/footer-logo1-45ae33115db81394d8bd25be65853b77.png)
Graph neural networks (GNN) have emerged as a new state-of-the-art for learning knowledge graph representations. Although they have shown impressive performance in recent studies, how to efficiently and effectively aggregate neighboring features is not well designed. To tackle this challenge, we propose the simplifying heterogeneous graph neural network (SHGNet), a generic framework that discards the two standard operations in GNN, including the transformation matrix and nonlinear activation. SHGNet, in particular, adopts only the essential component of neighborhood aggregation in GNN and incorporates relation features into feature propagation. Furthermore, to capture complex structures, SHGNet utilizes a hierarchical aggregation architecture, including node aggregation and relation weighting. Thus, the proposed model can treat each relation differently and selectively aggregate informative features. SHGNet has been evaluated for link prediction tasks on three real-world benchmark datasets. The experimental results show that SHGNet significantly promotes efficiency while maintaining superior performance, outperforming all the existing models in 3 out of 4 metrics on NELL-995 and in 4 out of 4 metrics on FB15k-237 dataset.
Recommendations
Representation learning of large-scale knowledge graphs via entity feature combinations.
Knowledge graphs are typical large-scale multi-relational structures, which comprise a large amount of fact triplets. Nonetheless, existing knowledge graphs are still sparse and far from being complete. To refine the knowledge graphs, representation ...
Re-evaluating Embedding-Based Knowledge Graph Completion Methods
Incompleteness of large knowledge graphs (KG) has motivated many researchers to propose methods to automatically find missing edges in KGs. A promising approach for KG completion (link prediction) is embedding a KG into a continuous vector space. There ...
Knowledge graph embedding model with attention-based high-low level features interaction convolutional network
Knowledge graphs are sizeable graph-structured knowledge with both abstract and concrete concepts in the form of entities and relations. Recently, convolutional neural networks have achieved outstanding results for more expressive ...
- We propose a knowledge graph embedding model with attention-based high-low level feature interaction convolutional network.
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Full Access
- Information
- Contributors
Published in
Elsevier Ltd
![](http://omraadeinfo.online/777/templates/cheerup1/res/banner1.gif)
In-Cooperation
Pergamon Press, Inc.
United States
Publication History
- Published: 1 July 2023
Author Tags
- Knowledge graphs
- Representation learning
- Knowledge graph embedding
- Link prediction
- research-article
Funding Sources
Other metrics.
- Bibliometrics
- Citations 1
Article Metrics
- 1 Total Citations View Citations
- 0 Total Downloads
- Downloads (Last 12 months) 0
- Downloads (Last 6 weeks) 0
Digital Edition
View this article in digital edition.
Share this Publication link
https://dlnext.acm.org/doi/10.1016/j.ipm.2023.103348
Share on Social Media
- 0 References
Export Citations
- Please download or close your previous search result export first before starting a new bulk export. Preview is not available. By clicking download, a status dialog will open to start the export process. The process may take a few minutes but once it finishes a file will be downloadable from your browser. You may continue to browse the DL while the export process is in progress. Download
- Download citation
- Copy citation
We are preparing your search results for download ...
We will inform you here when the file is ready.
Your file of search results citations is now ready.
Your search export query has expired. Please try again.
![](http://omraadeinfo.online/777/templates/cheerup1/res/banner1.gif)
IMAGES
VIDEO
COMMENTS
The main objective of knowledge graph representation learning (KGRL), also known as Knowledge Graph Embedding (KGE), is to acquire the embedded representation of entities and relations. ... we adopt the simplifying hierarchical feature propagation for heterogeneous KGs, which can deal with the rich semantic information and complex structure ...
Abstract. Graph neural networks (GNN) have emerged as a new state-of-the-art for learning knowledge graph representations. Although they have shown impressive performance in recent studies, how to efficiently and effectively aggregate neighboring features is not well designed.
In light of the above discussion, it is advisable to consider the computation efficiency and graph heterogeneity in feature propagation. In the present study, a novel simplifying heterogeneous graph neural network (SHGNet) for KGRL is proposed, which could effectively and efficiently learn knowledge graph representation learning.
DOI: 10.1016/j.ipm.2023.103348 Corpus ID: 257798623; Knowledge graph representation learning with simplifying hierarchical feature propagation @article{Li2023KnowledgeGR, title={Knowledge graph representation learning with simplifying hierarchical feature propagation}, author={Zhifei Li and Qi Zhang and Fangfang Zhu and Duantengchuan Li and Chao Zheng and Yan An Zhang}, journal={Inf. Process.
Request PDF | On Mar 1, 2023, Zhifei Li and others published Knowledge graph representation learning with simplifying hierarchical feature propagation | Find, read and cite all the research you ...
3.3.1. Hierarchical feature embedding. In this subsection, the multisource knowledge information S is used as the input of the hierarchical embedding network, where S = { S h m a p, S r m a p, S h _ r } ∈ ℜ k w × k h. k w and k h are the width and height of the knowledge source feature, respectively.
Knowledge graph representation learning with simplifying hierarchical feature propagation. Z Li, Q Zhang, F Zhu, D Li, C Zheng, Y Zhang. Information Processing & Management 60 (4), 103348, 2023. 16: 2023: Response speed enhanced fine-grained knowledge tracing: A multi-task learning perspective.
2.1 Knowledge Representation Learning Knowledge representation learning has been used to embed entities and relations in KGs into latent space and then infer missing facts based on existing ones. The literature falls into two major categories: (1) triplet-based methods that model triplet plausibility by score functions; (2) context-based meth-
Knowledge graph representation learning with simplifying hierarchical feature propagation. ... as an effective graph representation technique, have shown impressive performance in learning graph ...
Incorporating knowledge graph into recommendation is an effective way to alleviate data sparsity. Most existing knowledge-aware methods usually perform recursive embedding propagation by enumerating graph neighbors. However, the number of nodes' neighbors grows exponentially as the hop number increases, forcing the nodes to be aware of vast neighbors under this recursive propagation for ...
Knowledge graphs (KGs) can help enhance recommendations, especially for the data-sparsity scenarios with limited user-item interaction data. Due to the strong power of representation learning of graph neural networks (GNNs), recent works of KG-based recommendation deploy GNN models to learn from both knowledge graph and user-item bipartite interaction graph.
Representation learning models for Knowledge Graphs (KG) have proven to be effective in encoding structural information and performing reasoning over KGs. In this paper, we propose a novel pre-training-then-fine-tuning framework for knowledge graph representation learning, in which a KG model is firstly pre-trained with triple classification task, followed by discriminative fine-tuning on ...
In this paper, we propose TKRL model for representation learning of knowledge graphs with hierarchical types. We consider type information as projection matrices for entities, which are constructed with two hierarchical type encoders. Moreover, type information is also regarded as constraints in training and evaluation.
Knowledge graph representation learning with simplifying hierarchical feature propagation Abstract Graph neural networks (GNN) have emerged as a new state-of-the-art for learning knowledge graph representations.
Highlights • We propose a simplified GNN-based knowledge representation learning model with non-parametric feature propagation. • We design a hierarchical aggregation architecture to selectively ag...
A space-adaptive graph convolutional module is introduced, which could jointly explore the propagation process of user interest and social influence within a same semantic space and fail to simultaneously inject high-order connectivity information reflected in both user-item interaction graph and user-user social graph. Expand
Graph neural networks (GNNs) [21] aim to update the representations of nodes by aggregating the information from their neighbor nodes, which is a message propagation process. In this way, the node representations will obtain structural information and can be used for knowledge graph completion or other downstream tasks.
Knowledge graph representation learning with simplifying hierarchical feature propagation. ... This work proposes a novel knowledge graph representation model in complex space, namely MARS, to exploit complex relations to embed knowledge graphs, and significantly outperforms existing state-of-the-art models for link prediction and triple ...
ture expansion and feature propagationin graph and propose the learning framework with feature expansion. In the next section, we will discuss a typical feature propagation way, which has strong connection with the recent popular graph representationlearning method. 3 A Typical Way for Feature Propagation The typical way to expand node's ...
Representation learning of knowledge graphs aims to encode both entities and relations into a continuous low-dimensional vector space. Most existing methods only concentrate on learning representations with structured information located in triples, regardless of the rich information located in hierarchical types of entities, which could be collected in most knowledge graphs.
Link Prediction with Attention Applied on Multiple Knowledge Graph Embedding Models. Cosimo Gregucci M. Nayyeri D. Hern'andez Steffen Staab. Computer Science. WWW. 2023. TLDR. This paper combines the query representations from several models in a unified one to incorporate patterns that are independently captured by each model, and proves that ...
Knowledge Graph Embedding by Normalizing Flows. A unified perspective of embedding is proposed and uncertainty is introduced into KGE from the view of group theory to incorporate existing models and ensure the computation is tractable and enjoy the expressive power of complex random variables. Expand.