Kernel semi-supervised graph embedding model for multimodal and mixmodal data

Zhang, Qi; Li, Rui; Chu, Tianguang

doi:10.1007/s11432-018-9535-9

Search citation statements

Order By: Relevance

Paper Sections

Select...

Introduction1

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2020

2021

Publication Types

Select...

Article3

Other1

Relationship

Self Cite0

Independent4

Authors

Journals

Cited by 4 publications

(1 citation statement)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Traditional network embedding methods for dimensional reduction [2,3] have good performance on small network datasets. However, the complexity of these embedding methods is quadratic in the size of network vertices.…”

Section: Introductionmentioning

confidence: 99%

Representation learning on textual network with personalized PageRank

Dou

2021

Sci. China Inf. Sci.

View full text Add to dashboard Cite

Representation learning on textual network or textual network embedding, which leverages rich textual information associated with the network structure to learn low-dimensional embedding of vertices, has been useful in a variety of tasks. However, most approaches learn textual network embedding by using direct neighbors. In this paper, we employ a powerful and spatially localized operation: personalized PageRank (PPR) to eliminate the restriction of using only the direct connection relationship. Also, we analyze the relationship between PPR and spectral-domain theory, which provides insight into the empirical performance boost. From the experiment, we discovered that the proposed method provides a great improvement in linkprediction tasks, when compared to existing methods, achieving a new state-of-the-art on several real-world benchmark datasets.

show abstract

Section: Introductionmentioning

confidence: 99%