Learning High-order Structural and Attribute information by Knowledge Graph Attention Networks for Enhancing Knowledge Graph Embedding

2019-10-09 · Wenqiang Liu, Hongyun Cai, Xu Cheng, Sifa Xie, Yipeng Yu, Hanyu Zhang

The goal of representation learning of knowledge graph is to encode both entities and relations into a low-dimensional embedding spaces. Many recent works have demonstrated the benefits of knowledge graph embedding on knowledge graph completion task, such as relation extraction. However, we observe that: 1) existing method just take direct relations between entities into consideration and fails to express high-order structural relationship between entities; 2) these methods just leverage relation triples of KGs while ignoring a large number of attribute triples that encoding rich semantic information. To overcome these limitations, this paper propose a novel knowledge graph embedding method, named KANE, which is inspired by the recent developments of graph convolutional networks (GCN). KANE can capture both high-order structural and attribute information of KGs in an efficient, explicit and unified manner under the graph convolutional networks framework. Empirical results on three datasets show that KANE significantly outperforms seven state-of-arts methods. Further analysis verify the efficiency of our method and the benefits brought by the attention mechanism.

📄 PDF Abstract BibTeX arXiv:1910.03891

Code (0)

등록된 구현이 없습니다.

Tasks

AttributeGraph AttentionGraph Embedding Knowledge Graph Completion Knowledge Graph EmbeddingRelationRelation Extraction Representation Learning

Methods 이 논문이 사용한 방법론

Graph Convolutional Networks 설명 없음

Incorporating Higher-order Structural Information for Graph Clustering

2024-03-17 · Qiankun Li, Haobing Liu, Ruobing Jiang, Tingting Wang

Clustering holds profound significance in data mining. In recent years, graph convolutional network (GCN) has emerged as a powerful tool for deep clustering, integrating both graph structural information and node attribu…

Clustering Deep Clustering Graph Clustering

Hypergraph Foundation Model

2025-03-03 · Yifan Feng, Shiquan Liu, Xiangmin Han, Shaoyi Du 외

Hypergraph neural networks (HGNNs) effectively model complex high-order relationships in domains like protein interactions and social networks by connecting multiple vertices through hyperedges, enhancing modeling capabi…

Diversity model

Incorporating Attributes and Multi-Scale Structures for Heterogeneous Graph Contrastive Learning

2025-03-18 · Ruobing Jiang, Yacong Li, Haobing Liu, Yanwei Yu

Heterogeneous graphs (HGs) are composed of multiple types of nodes and edges, making it more effective in capturing the complex relational structures inherent in the real world. However, in real-world scenarios, labeled …

Attribute Contrastive Learning Representation Learning Self-Supervised Learning

HyperBERT: Mixing Hypergraph-Aware Layers with Language Models for Node Classification on Text-Attributed Hypergraphs

2024-02-11 · Adrián Bazaga, Pietro Liò, Gos Micklem

Hypergraphs are characterized by complex topological structure, representing higher-order interactions among multiple entities through hyperedges. Lately, hypergraph-based deep learning methods to learn informative data …

Inductive Bias Language Modeling Language Modelling Node Classification

Str-GCL: Structural Commonsense Driven Graph Contrastive Learning

2025-07-09 · Dongxiao He, Yongqi Huang, Jitao Zhao, Xiaobao Wang 외 arxiv

Graph Contrastive Learning (GCL) is a widely adopted approach in self-supervised graph representation learning, applying contrastive objectives to produce effective representations. However, current GCL methods primarily…

Graph Representation Learning Contrastive Learning