Distributed Representations of Entities in Open-World Knowledge Graphs

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Guo, Lingbing, Chen, Zhuo, Chen, Jiaoyan, Zhang, Yichi, Sun, Zequn, Bo, Zhongpo, Fang, Yin, Liu, Xiaoze, Chen, Huajun, Zhang, Wen
Natura: Preprint
Pubblicazione: 2020
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913297854365696
author Guo, Lingbing
Chen, Zhuo
Chen, Jiaoyan
Zhang, Yichi
Sun, Zequn
Bo, Zhongpo
Fang, Yin
Liu, Xiaoze
Chen, Huajun
Zhang, Wen
author_facet Guo, Lingbing
Chen, Zhuo
Chen, Jiaoyan
Zhang, Yichi
Sun, Zequn
Bo, Zhongpo
Fang, Yin
Liu, Xiaoze
Chen, Huajun
Zhang, Wen
contents Graph neural network (GNN)-based methods have demonstrated remarkable performance in various knowledge graph (KG) tasks. However, most existing approaches rely on observing all entities during training, posing a challenge in real-world knowledge graphs where new entities emerge frequently. To address this limitation, we introduce Decentralized Attention Network (DAN). DAN leverages neighbor context as the query vector to score the neighbors of an entity, thereby distributing the entity semantics only among its neighbor embeddings. To effectively train a DAN, we introduce self-distillation, a technique that guides the network in generating desired representations. Theoretical analysis validates the effectiveness of our approach. We implement an end-to-end framework and conduct extensive experiments to evaluate our method, showcasing competitive performance on conventional entity alignment and entity prediction tasks. Furthermore, our method significantly outperforms existing methods in open-world settings.
format Preprint
id arxiv_https___arxiv_org_abs_2010_08114
institution arXiv
publishDate 2020
record_format arxiv
spellingShingle Distributed Representations of Entities in Open-World Knowledge Graphs
Guo, Lingbing
Chen, Zhuo
Chen, Jiaoyan
Zhang, Yichi
Sun, Zequn
Bo, Zhongpo
Fang, Yin
Liu, Xiaoze
Chen, Huajun
Zhang, Wen
Machine Learning
Artificial Intelligence
Computation and Language
Graph neural network (GNN)-based methods have demonstrated remarkable performance in various knowledge graph (KG) tasks. However, most existing approaches rely on observing all entities during training, posing a challenge in real-world knowledge graphs where new entities emerge frequently. To address this limitation, we introduce Decentralized Attention Network (DAN). DAN leverages neighbor context as the query vector to score the neighbors of an entity, thereby distributing the entity semantics only among its neighbor embeddings. To effectively train a DAN, we introduce self-distillation, a technique that guides the network in generating desired representations. Theoretical analysis validates the effectiveness of our approach. We implement an end-to-end framework and conduct extensive experiments to evaluate our method, showcasing competitive performance on conventional entity alignment and entity prediction tasks. Furthermore, our method significantly outperforms existing methods in open-world settings.
title Distributed Representations of Entities in Open-World Knowledge Graphs
topic Machine Learning
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2010.08114