<abstract xmlns="http://www.w3.org/1999/xhtml">

<sec><h3>Purpose</h3>
<p>Based on real-world academic data, this study aims to use network embedding technology to mining academic relationships, and investigate the effectiveness of the proposed embedding model on academic collaborator recommendation tasks.</p>
</sec>
<sec><h3>Design/methodology/approach</h3>
<p>We propose an academic collaborator recommendation model based on attributed network embedding (ACR-ANE), which can get enhanced scholar embedding and take full advantage of the topological structure of the network and multi-type scholar attributes. The non-local neighbors for scholars are defined to capture strong relationships among scholars. A deep auto-encoder is adopted to encode the academic collaboration network structure and scholar attributes into a low-dimensional representation space.</p>
</sec>
<sec><h3>Findings</h3>
<p>1. The proposed non-local neighbors can better describe the relationships among scholars in the real world than the first-order neighbors. 2. It is important to consider the structure of the academic collaboration network and scholar attributes when recommending collaborators for scholars simultaneously.</p>
</sec>
<sec><h3>Research limitations</h3>
<p>The designed method works for static networks, without taking account of the network dynamics.</p>
</sec>
<sec><h3>Practical implications</h3>
<p>The designed model is embedded in academic collaboration network structure and scholarly attributes, which can be used to help scholars recommend potential collaborators.</p>
</sec>
<sec><h3>Originality/value</h3>
<p>Experiments on two real-world scholarly datasets, Aminer and APS, show that our proposed method performs better than other baselines.</p>
</sec>
</abstract>

Purpose
Based on real-world academic data, this study aims to use network embedding technology to mining academic relationships, and investigate the effectiveness of the proposed embedding model on academic collaborator recommendation tasks.

Design/methodology/approach
We propose an academic collaborator recommendation model based on attributed network embedding (ACR-ANE), which can get enhanced scholar embedding and take full advantage of the topological structure of the network and multi-type scholar attributes. The non-local neighbors for scholars are defined to capture strong relationships among scholars. A deep auto-encoder is adopted to encode the academic collaboration network structure and scholar attributes into a low-dimensional representation space.

Findings
1. The proposed non-local neighbors can better describe the relationships among scholars in the real world than the first-order neighbors. 2. It is important to consider the structure of the academic collaboration network and scholar attributes when recommending collaborators for scholars simultaneously.

Research limitations
The designed method works for static networks, without taking account of the network dynamics.

Practical implications
The designed model is embedded in academic collaboration network structure and scholarly attributes, which can be used to help scholars recommend potential collaborators.

Originality/value
Experiments on two real-world scholarly datasets, Aminer and APS, show that our proposed method performs better than other baselines.

Academic Collaborator Recommendation Based on Attributed Network Embedding

School of Computer and Information Science

Journal of Data and Information Science

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

{"article-title":"Academic Collaborator Recommendation Based on Attributed Network Embedding"}

Purpose
Based on real-world academic data, this study aims to use network embedding technology to mining academic relationships, and investigate the...

Notation	Description
G	The attributed academic collaboration network
V	The set of all scholars
E	The set of relationship between scholars
S	The weight of edge
A	Scholar attribute matrix
X	Adjacency matrix of multi-relational networks
Y	Final scholar embedding matrix
d	Scholar embedding dimension
d_a	Scholar attribute embedding dimension
x_i, ${\hat{x}}_{i}$ {{{\boldsymbol{\hat x}}}_{\boldsymbol{i}}}	The input data and reconstructed data
W^(k), Ŵ^(k)	The k-th layer weight matrix
b^(k), ${\hat{b}}^{(k)}$ {{{\boldsymbol{\hat b}}}^{{\boldsymbol{(k)}}}}	The k-th layer biases

Datasets	# of Nodes	# of Links
Aminer	7,436	11,568
APS	5,102	39,333

Academic Collaborator Recommendation Based on Attributed Network Embedding

Article Category: Research Paper

Online veröffentlicht: 03. Feb. 2022

Seitenbereich: 37 - 56

Eingereicht: 10. Nov. 2021

Akzeptiert: 11. Jan. 2022

DOI: https://doi.org/10.2478/jdis-2022-0005

Schlüsselwörter
Academic relationships mining, Collaborator recommendation, Attributed network embedding, Deep learning

© 2022 Ouxia Du et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Notations.

Statistics of two datasets.

Academic Collaborator Recommendation Based on Attributed Network Embedding

Article Category: Research Paper

Online veröffentlicht: 03. Feb. 2022

Seitenbereich: 37 - 56

Eingereicht: 10. Nov. 2021

Akzeptiert: 11. Jan. 2022

DOI: https://doi.org/10.2478/jdis-2022-0005

SchlüsselwörterAcademic relationships mining, Collaborator recommendation, Attributed network embedding, Deep learning

© 2022 Ouxia Du et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Notations.

Statistics of two datasets.

Schlüsselwörter
Academic relationships mining, Collaborator recommendation, Attributed network embedding, Deep learning