Results 1 to 10 of about 244,866 (345)

Entity-Agnostic Representation Learning for Parameter-Efficient Knowledge Graph Embedding [PDF]

AAAI Conference on Artificial Intelligence, 2023
We propose an entity-agnostic representation learning method for handling the problem of inefficient parameter storage costs brought by embedding knowledge graphs.
Mingyang Chen, Wen Zhang, Zhen Yao, Yushan Zhu, Yang Gao, Jeff Z. Pan, Hua-zeng Chen   +6 more
semanticscholar   +1 more source

Enriching Translation-Based Knowledge Graph Embeddings Through Continual Learning

IEEE Access, 2018
This paper addresses an enrichment of translation-based knowledge graph embeddings. When new knowledge triples become available after a knowledge graph is embedded onto a vector space, the embedding should be enriched with the new triples, but without ...
Hyun-Je Song, Seong-Bae Park
doaj   +1 more source

Recommender Systems Based on Graph Embedding Techniques: A Review

IEEE Access, 2022
As a pivotal tool to alleviate the information overload problem, recommender systems aim to predict user’s preferred items from millions of candidates by analyzing observed user-item relations.
Yue Deng
doaj   +1 more source

Knowledge Graph Embedding via Dynamic Mapping Matrix

Annual Meeting of the Association for Computational Linguistics, 2015
Knowledge graphs are useful resources for numerous AI applications, but they are far from completeness. Previous work such as TransE, TransH and TransR/CTransR regard a relation as translation from head entity to tail entity and the CTransR achieves ...
Guoliang Ji, Shizhu He, Liheng Xu, Kang Liu, Jun Zhao   +4 more
semanticscholar   +1 more source

Towards Continual Knowledge Graph Embedding via Incremental Distillation [PDF]

AAAI Conference on Artificial Intelligence
Traditional knowledge graph embedding (KGE) methods typically require preserving the entire knowledge graph (KG) with significant training costs when new knowledge emerges.
Jiajun Liu, Wenjun Ke, Peng Wang, Ziyu Shang, Jinhua Gao, Guozheng Li, Ke Ji, Yanhe Liu   +7 more
semanticscholar   +1 more source

Multitask feature learning approach for knowledge graph enhanced recommendations with RippleNet.

PLoS ONE, 2021
Introducing a knowledge graph into a recommender system as auxiliary information can effectively solve the sparse and cold start problems existing in traditional recommender systems. In recent years, many researchers have performed related work.
YueQun Wang, LiYan Dong, YongLi Li, Hao Zhang   +3 more
doaj   +1 more source

Bootstrapping Entity Alignment with Knowledge Graph Embedding

International Joint Conference on Artificial Intelligence, 2018
Embedding-based entity alignment represents different knowledge graphs (KGs) as low-dimensional embeddings and finds entity alignment by measuring the similarities between entity embeddings.
Zequn Sun, Wei Hu, Qingheng Zhang, Yuzhong Qu   +3 more
semanticscholar   +1 more source

Knowledge Graph Embedding via Graph Attenuated Attention Networks

IEEE Access, 2020
Knowledge graphs contain a wealth of real-world knowledge that can provide strong support for artificial intelligence applications. Much progress has been made in knowledge graph completion, state-of-the-art models are based on graph convolutional neural
Rui Wang, Bicheng Li, Shengwei Hu, Wenqian Du, Min Zhang   +4 more
doaj   +1 more source

MöbiusE: Knowledge Graph Embedding on Möbius ring

, 2021
In this work, we propose a novel Knowledge Graph Embedding (KGE) strategy, called MöbiusE, in which the entities and relations are embedded to the surface of a Möbius ring.
Xiong, W, Liu, J, Wen, S, Chen, Y, Zhang, Z   +4 more
core   +1 more source

Triple Context-Based Knowledge Graph Embedding

IEEE Access, 2018
Knowledge graph embedding aims to represent entities and relations of a knowledge graph in continuous vector spaces. It has increasingly drawn attention for its ability to encode semantics in low dimensional vectors as well as its outstanding performance
Huan Gao, Jun Shi, Guilin Qi, Meng Wang
doaj   +1 more source