Content-Structural Relation Inference in Knowledge Base

Zeya, Zhao; Jia, Yunyi; Wang, Yuanzhuo; Cheng, Xueqi

doi:10.1609/aaai.v28i1.9085

Cited by 7 publications

(2 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The rule reasoning based on the global structure performs path mining on the entire knowledge graph, and approximately regards the paths between some entities as rules to determine whether there is a specified relationship between entities. There are literatures in this area [26][27][28][29][30][31][32][33][34][35][36][37][38]. The rule reasoning that introduces the local structure is to reason on the local structure, and the typical researches are in the literature [39,40].…”

Section: Knowledge Reasoningmentioning

confidence: 99%

A survey of hybrid knowledge reasoning oriented to KG

Huang

Wang

et al. 2022

International Conference on Computer, Artificial Intelligence, and Control Engineering (CAICE 2022)

View full text Add to dashboard Cite

Knowledge reasoning is a key technology for constructing knowledge graphs and realizing knowledge graph completion. A single category of reasoning has its own advantages and disadvantages, so hybrid reasoning, which integrates the advantages of multiple single reasoning methods, has become a hot research direction. This paper will briefly introduce the background and definition of hybrid reasoning, introduce the classification of knowledge reasoning oriented to knowledge graph in detail, and then focus on the research progress, future research directions and possible challenges of hybrid reasoning in recent years.

show abstract

Section: Knowledge Reasoningmentioning

confidence: 99%

A survey of hybrid knowledge reasoning oriented to KG

Huang

Wang

et al. 2022

International Conference on Computer, Artificial Intelligence, and Control Engineering (CAICE 2022)

View full text Add to dashboard Cite

show abstract

“…Namely, it predicts t given (h, r) or predict h given (r, t). Similar to the setting in (Bordes et al 2011;2013;Zhao, Jia, and Wang 2014) best answer, and we conduct the link prediction task on the two data sets WN18 and FB15K. Following the procedure used in (Bordes et al 2013), we also adopt the evaluation measure, namely, mean rank (i.e., mean rank of correct entities).…”

Section: Link Predictionmentioning

confidence: 99%

Locally Adaptive Translation for Knowledge Graph Embedding

Jia

Wang

Lin

et al. 2016

AAAI

Self Cite

View full text Add to dashboard Cite

Knowledge graph embedding aims to represent entities and relations in a large-scale knowledge graph as elements in a continuous vector space. Existing methods, e.g., TransE and TransH, learn embedding representation by defining a global margin-based loss function over the data. However, the optimal loss function is determined during experiments whose parameters are examined among a closed set of candidates. Moreover, embeddings over two knowledge graphs with different entities and relations share the same set of candidate loss functions, ignoring the locality of both graphs. This leads to the limited performance of embedding related applications. In this paper, we propose a locally adaptive translation method for knowledge graph embedding, called TransA, to find the optimal loss function by adaptively determining its margin over different knowledge graphs. Experiments on two benchmark data sets demonstrate the superiority of the proposed method, as compared to the-state-of-the-art ones.

show abstract