Journal Article10.1109/TNNLS.2021.3055147
Learning Knowledge Graph Embedding With Heterogeneous Relation Attention Networks.
274
TL;DR: Wang et al. as discussed by the authors proposed a heterogeneous GNNs framework based on attention mechanism, where the neighbor features of an entity are first aggregated under each relation-path, and then the importance of different relationpaths is learned through the relation features.
read more
Abstract: Knowledge graph (KG) embedding aims to study the embedding representation to retain the inherent structure of KGs. Graph neural networks (GNNs), as an effective graph representation technique, have shown impressive performance in learning graph embedding. However, KGs have an intrinsic property of heterogeneity, which contains various types of entities and relations. How to address complex graph data and aggregate multiple types of semantic information simultaneously is a critical issue. In this article, a novel heterogeneous GNNs framework based on attention mechanism is proposed. Specifically, the neighbor features of an entity are first aggregated under each relation-path. Then the importance of different relation-paths is learned through the relation features. Finally, each relation-path-based features with the learned weight values are aggregated to generate the embedding representation. Thus, the proposed method not only aggregates entity features from different semantic aspects but also allocates appropriate weights to them. This method can capture various types of semantic information and selectively aggregate informative features. The experiment results on three real-world KGs demonstrate superior performance when compared with several state-of-the-art methods.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Knowledge Graphs: Opportunities and Challenges
TL;DR: In this paper , the authors present a systematic overview of knowledge graph research and discuss severe technical challenges in this field, such as knowledge graph embeddings, knowledge acquisition, knowledge graph completion, knowledge fusion, and knowledge reasoning.
215
NGDNet: Nonuniform Gaussian-label distribution learning for infrared head pose estimation and on-task behavior understanding in the classroom
TL;DR: Ting et al. as mentioned in this paper proposed a novel non-uniform Gaussian-label distribution learning network (NGDNet) for the HPE task, which revealed the essential properties from two different perspectives: 1) two head pose images change differently in pitch and yaw directions with the same angle increasing on the central pose; 2) the IR head pose variation first increases and then decreases in the pitch direction.
101
A Comprehensive Survey of Graph Neural Networks for Knowledge Graphs
TL;DR: This study is aimed at providing a broad, complete as well as comprehensive overview of GNN-based technologies for solving four different KG tasks, including link prediction, knowledge graph alignment, knowledge graphs reasoning, and node classification.
Overview of behavior recognition based on deep learning
TL;DR: This paper systemizes and introduces behavior recognition algorithms based on deep learning proposed in recent years, then focuses on a series of behavior recognition algorithm based on image and bone data; deeply analyzes their theories and performance, and puts forward further prospects.
62
A Review of Knowledge Graph Completion
TL;DR: The task of knowledge graph completion is divided into conventional and graph neural network representation learning and graphs in more detail, which aims to predict unknown triples based on previously visited triples.
References
WordNet: a lexical database for English
TL;DR: WordNet1 provides a more effective combination of traditional lexicographic information and modern computing, and is an online lexical database designed for use under program control.
16.9K
Graph Attention Networks
Petar Veličković,Guillem Cucurull,Arantxa Casanova,Adriana Romero,Pietro Liò,Yoshua Bengio +5 more
- 15 Feb 2018
TL;DR: Graph Attention Networks (GATs) as mentioned in this paper leverage masked self-attentional layers to address the shortcomings of prior methods based on graph convolutions or their approximations.
•Posted Content
Inductive Representation Learning on Large Graphs
TL;DR: GraphSAGE is presented, a general, inductive framework that leverages node feature information (e.g., text attributes) to efficiently generate node embeddings for previously unseen data and outperforms strong baselines on three inductive node-classification benchmarks.
11.9K
•Proceedings Article
Translating Embeddings for Modeling Multi-relational Data
Antoine Bordes,Nicolas Usunier,Alberto Garcia-Duran,Jason Weston,Oksana Yakhnenko +4 more
- 05 Dec 2013
TL;DR: TransE is proposed, a method which models relationships by interpreting them as translations operating on the low-dimensional embeddings of the entities, which proves to be powerful since extensive experiments show that TransE significantly outperforms state-of-the-art methods in link prediction on two knowledge bases.
A Comprehensive Survey on Graph Neural Networks
TL;DR: This article provides a comprehensive overview of graph neural networks (GNNs) in data mining and machine learning fields and proposes a new taxonomy to divide the state-of-the-art GNNs into four categories, namely, recurrent GNNS, convolutional GNN’s, graph autoencoders, and spatial–temporal Gnns.