Hierarchical Random Walk Inference in Knowledge Graphs

Liu, Qiao; Jiang, Liuyi; Minghao, Han; Liu, Yao; Qin, Zhiguang

doi:10.1145/2911451.2911509

Cited by 24 publications

(8 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The highest result for each column is shown in bold. The results of TransE and TorusE were reported by Ebisu and Ichise (2018), the results of RESCAL were reported by Nickel et al (2016), the results of DistMult and ComplEx were reported by Trouillon et al (2016), the results of R-GCN and ConvE were reported by Dettmers et al (2018), the results of PRA were reported by Liu et al (2016), and the results of Node+LinkFeat were reported by Toutanova and Chen (2015).…”

Section: Evaluation Of Gpars As Entity Ranking Systemmentioning

confidence: 89%

“…However, it has also been shown that the Node+LinkFeat model cannot deal with a lowredundancy dataset because the model uses information which is too local. On the other hand, it has shown that a logistic regression model, the PRA model (Lao and Cohen, 2010;Lao et al, 2011), which utilizes multi-hop information do not have sufficient accuracy (Liu et al, 2016). This suggests logistic regression does not have enough power to deal with deep information.…”

Section: Observed Feature Modelsmentioning

confidence: 99%

See 1 more Smart Citation

Graph Pattern Entity Ranking Model for Knowledge Graph Completion

Ebisu

Ichise

2019

Proceedings of the 2019 Conference of the North

View full text Add to dashboard Cite

Knowledge graphs have evolved rapidly in recent years and their usefulness has been demonstrated in many artificial intelligence tasks. However, knowledge graphs often have lots of missing facts. To solve this problem, many knowledge graph embedding models have been developed to populate knowledge graphs and these have shown outstanding performance. However, knowledge graph embedding models are so-called black boxes, and the user does not know how the information in a knowledge graph is processed and the models can be difficult to interpret. In this paper, we utilize graph patterns in a knowledge graph to overcome such problems. Our proposed model, the graph pattern entity ranking model (GRank), constructs an entity ranking system for each graph pattern and evaluates them using a ranking measure. By doing so, we can find graph patterns which are useful for predicting facts. Then, we perform link prediction tasks on standard datasets to evaluate our GRank method. We show that our approach outperforms other state-of-the-art approaches such as ComplEx and TorusE for standard metrics such as HITS@n and MRR. Moreover, our model is easily interpretable because the output facts are described by graph patterns.

show abstract

Section: Evaluation Of Gpars As Entity Ranking Systemmentioning

confidence: 89%

Section: Observed Feature Modelsmentioning

confidence: 99%

Graph Pattern Entity Ranking Model for Knowledge Graph Completion

Ebisu

Ichise

2019

Proceedings of the 2019 Conference of the North

View full text Add to dashboard Cite

show abstract

“…Using latent context of the text, the model obtains additional improvement. Liu et al [109] developed a new random walk based learning algorithm named Hierarchical Random-walk inference (HiRi). It is a two-tier scheme: the upper tier recognizes relational sequence pattern, and the lower tier captures information from subgraphs of knowledge bases.…”

Section: Random Walk Based Methodsmentioning

confidence: 99%

Graph Learning: A Survey

Xia

Sun

et al. 2021

IEEE Trans. Artif. Intell.

297

View full text Add to dashboard Cite

Graphs are widely used as a popular representation of the network structure of connected data. Graph data can be found in a broad spectrum of application domains such as social systems, ecosystems, biological networks, knowledge graphs, and information systems. With the continuous penetration of artificial intelligence technologies, graph learning (i.e., machine learning on graphs) is gaining attention from both researchers and practitioners. Graph learning proves effective for many tasks, such as classification, link prediction, and matching. Generally, graph learning methods extract relevant features of graphs by taking advantage of machine learning algorithms. In this survey, we present a comprehensive overview on the state-of-the-art of graph learning. Special attention is paid to four categories of existing graph learning methods, including graph signal processing, matrix factorization, random walk, and deep learning. Major models and algorithms under these categories are reviewed respectively. We examine graph learning applications in areas such as text, images, science, knowledge graphs, and combinatorial optimization. In addition, we discuss several promising research directions in this field.

show abstract

“…In order to learn more informative entity representations, existing approaches [8,11] update a node representation by the propagation along the graph and the aggregation of neighboring nodes, which can be regarded as reasoning process. However, these models simply treat the reasoning direction as arbitrary.…”

Section: Introductionmentioning

confidence: 99%

Integrating Subgraph-Aware Relation and Direction Reasoning for Question Answering

Wang

Zhao

Cheng

et al. 2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Question Answering (QA) models over Knowledge Bases (KBs) are capable of providing more precise answers by utilizing relation information among entities. Although effective, most of these models solely rely on fixed relation representations to obtain answers for different question-related KB subgraphs. Hence, the rich structured information of these subgraphs may be overlooked by the relation representation vectors. Meanwhile, the direction information of reasoning, which has been proven effective for the answer prediction on graphs, has not been fully explored in existing work. To address these challenges, we propose a novel neural model, Relation-updated Direction-guided Answer Selector (RDAS), which converts relations in each subgraph to additional nodes to learn structure information. Additionally, we utilize direction information to enhance the reasoning ability. Experimental results show that our model yields substantial improvements on two widely used datasets.

show abstract

Hierarchical Random Walk Inference in Knowledge Graphs

Cited by 24 publications

References 19 publications

Graph Pattern Entity Ranking Model for Knowledge Graph Completion

Graph Pattern Entity Ranking Model for Knowledge Graph Completion

Graph Learning: A Survey

Integrating Subgraph-Aware Relation and Direction Reasoning for Question Answering

Contact Info

Product

Resources

About