Journal Home > Volume 29 , Issue 2

Metapaths with specific complex semantics are critical to learning diverse semantic and structural information of heterogeneous networks (HNs) for most of the existing representation learning models. However, any metapaths consisting of multiple, simple metarelations must be driven by domain experts. These sensitive, expensive, and limited metapaths severely reduce the flexibility and scalability of the existing models. A metapath-free, scalable representation learning model, called Metarelation2vec, is proposed for HNs with biased joint learning of all metarelations in a bid to address this problem. Specifically, a metarelation-aware, biased walk strategy is first designed to obtain better training samples by using autogenerating cooperation probabilities for all metarelations rather than using expert-given metapaths. Thereafter, grouped nodes by the type, a common and shallow skip-gram model is used to separately learn structural proximity for each node type. Next, grouped links by the type, a novel and shallow model is used to separately learn the semantic proximity for each link type. Finally, supervised by the cooperation probabilities of all meta-words, the biased training samples are thrown into the shallow models to jointly learn the structural and semantic information in the HNs, ensuring the accuracy and scalability of the models. Extensive experimental results on three tasks and four open datasets demonstrate the advantages of our proposed model.


menu
Abstract
Full text
Outline
About this article

Metarelation2vec: A Metapath-Free Scalable Representation Learning Model for Heterogeneous Networks

Show Author's information Lei Chen1( )Yuan Li1Yong Lei2Xingye Deng1
School of Information and Electrical Engineering, Hunan University of Science and Technology, Xiangtan 411201, China
School of Computer Science and Engineering, Hunan University of Science and Technology, Xiangtan 411201, China

Abstract

Metapaths with specific complex semantics are critical to learning diverse semantic and structural information of heterogeneous networks (HNs) for most of the existing representation learning models. However, any metapaths consisting of multiple, simple metarelations must be driven by domain experts. These sensitive, expensive, and limited metapaths severely reduce the flexibility and scalability of the existing models. A metapath-free, scalable representation learning model, called Metarelation2vec, is proposed for HNs with biased joint learning of all metarelations in a bid to address this problem. Specifically, a metarelation-aware, biased walk strategy is first designed to obtain better training samples by using autogenerating cooperation probabilities for all metarelations rather than using expert-given metapaths. Thereafter, grouped nodes by the type, a common and shallow skip-gram model is used to separately learn structural proximity for each node type. Next, grouped links by the type, a novel and shallow model is used to separately learn the semantic proximity for each link type. Finally, supervised by the cooperation probabilities of all meta-words, the biased training samples are thrown into the shallow models to jointly learn the structural and semantic information in the HNs, ensuring the accuracy and scalability of the models. Extensive experimental results on three tasks and four open datasets demonstrate the advantages of our proposed model.

Keywords: representation learning, random walk, heterogeneous network, metarelation, metapath

References(27)

[1]
L. Tseng, L. Wong, S. Otoum, M. Aloqaily, and J. Ben Othman, Blockchain for managing heterogeneous Internet of Things: A perspective architecture, IEEE Netw., vol. 34, no. 1, pp. 16–23, 2020.
[2]
K. Yang, J. Zhu, and X. Guo, POI neural-rec model via graph embedding representation, Tsinghua Science and Technology, vol. 26, no. 2, pp. 208–218, 2020.
[3]
L. Chen, F. Chen, Z. Liu, M. Lv, T. He, and S. Zhang, Parallel gravitational clustering based on grid partitioning for large-scale data, Appl. Intell., vol. 53, no. 3, pp. 2506–2526, 2023.
[4]
Y. Xie, B. Yu, S. Lv, C. Zhang, G. Wang, and M. Gong, A survey on heterogeneous network representation learning, Pattern Recognit., vol. 116, p. 107936, 2021.
[5]
D. Sun, Z. Huang, D. Li, and M. Guo, Efficient knowledge graph embedding training framework with multiple GPUs, Tsinghua Science and Technology, vol. 28, no. 1, pp. 167–175, 2022.
[6]
L. Chen, Q. Guo, Z. Liu, S. Zhang, and H. Zhang, Enhanced synchronization-inspired clustering for high-dimensional data, Complex Intell. Syst., vol. 7, no. 1, pp. 203–223, 2021.
[7]
H. D. Bedru, S. Yu, X. Xiao, D. Zhang, L. Wan, H. Guo, and F. Xia, Big networks: A survey, Comput. Sci. Rev., vol. 37, p. 100247, 2020.
[8]
B. Li and D. Pi, Network representation learning: A systematic literature review, Neural Comput. Appl., vol. 32, no. 21, pp. 16647–16679, 2020.
[9]
Y. Hu, D. Li, P. Sun, P. Yi, and J. Wu, Polymorphic smart network: An open, flexible and universal architecture for future heterogeneous networks, IEEE Trans. Netw. Sci. Eng., vol. 7, no. 4, pp. 2515–2525, 2020.
[10]
L. Chen, Y. Li, X. Deng, Z. Liu, M. Lv, and T. He, Semantic-aware network embedding via optimized random walk and paragaraph2vec, J. Comput. Sci., vol. 63, p. 101825, 2022.
[11]
R. Hussein, D. Yang, and P. Cudré-Mauroux, Are meta-paths necessary? Revisiting heterogeneous graph embeddings, in Proc. 27th ACM Int. Conf. Information and Knowledge Management, Torino, Italy, 2018, pp. 437–446.
[12]
Z. Li, X. Wang, J. Li, and Q. Zhang, Deep attributed network representation learning of complex coupling and interaction, Knowl. Based Syst., vol. 212, p. 106618, 2021.
[13]
Y. Dong, N. V. Chawla, and A. Swami, metapath2vec: Scalable representation learning for heterogeneous networks, in Proc. 23rd ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining, Halifax, Canada, 2017, pp. 135–144.
[14]
X. Wang, H. Ji, C. Shi, B. Wang, Y. Ye, P. Cui, and P. S. Yu, Heterogeneous graph attention network, in Proc. WWW’19: The World Wide Web Conference, San Francisco, CA, USA, 2019, pp. 2022–2032.
[15]
X. Fu, J. Zhang, Z. Meng, and I. King, MAGNN: Metapath aggregated graph neural network for heterogeneous graph embedding, in Proc. The Web Conference 2020, Taipei, China, 2020, pp. 2331–2341.
[16]
B. Hu, Y. Fang, and C. Shi, Adversarial learning on heterogeneous information networks, in Proc. 25th ACM SIGKDD Int. Conf. Knowledge Discovery & Data Mining, Anchorage, AK, USA, 2019, pp. 120–129.
[17]
X. Wang, D. Bo, C. Shi, S. Fan, Y. Ye, and P. S. Yu, A survey on heterogeneous graph embedding: Methods, techniques, applications and sources, IEEE Trans. Big Data, vol. 9, no. 2, pp. 415–436, 2023.
[18]
H. Gui, J. Liu, F. Tao, M. Jiang, B. Norick, L. Kaplan, and J. Han, Embedding learning with events in heterogeneous information networks, IEEE Trans. Knowl. Data Eng., vol. 29, no. 11, pp. 2428–2441, 2017.
[19]
D. Zhang, J. Yin, X. Zhu, and C. Zhang, Network representation learning: A survey, IEEE Trans. Big Data, vol. 6, no. 1, pp. 3–28, 2020.
[20]
C. Zhang, A. Swami, and N. V. Chawla, SHNE: Representation learning for semantic-associated heterogeneous networks, in Proc. 12th ACM Int. Conf. Web Search and Data Mining, Melbourne, Australia, 2019, pp. 690–698.
[21]
S. Yun, M. Jeong, R. Kim, J. Kang, and H. J. Kim, Graph transformer networks, arXiv preprint arXiv:1911.06455, 2019.
[22]
S. Zhou, J. Bu, X. Wang, J. Chen, and C. Wang, HAHE: Hierarchical attentive heterogeneous information network embedding, arXiv preprint arXiv: 1902.01475, 2019.
[23]
L. Chen, H. Zheng, Y. Li, Z. Liu, L. Zhao, and H. Tang, Enhanced density peak-based community detection algorithm, J. Intell. Inf. Syst., vol. 59, no. 2, pp. 263–284, 2022.
[24]
D. Zhang, J. Yin, X. Zhu, and C. Zhang, MetaGraph2Vec: Complex semantic path augmented heterogeneous network embedding, presented at 22nd Pacific-Asia Conference on Knowledge Discovery and Data Mining, Melbourne, Australia, 2018.
[25]
W. Zhang, Y. Fang, Z. Liu, M. Wu, and X. Zhang, mg2vec: Learning relationship-preserving heterogeneous graph representations via metagraph embedding, IEEE Trans. Knowl. Data Eng., vol. 34, no. 3, pp. 1317–1329, 2022.
[26]
A. Sankar, X. Zhang, and K. C. C. Chang, Meta-GNN: Metagraph neural network for semi-supervised learning in attributed heterogeneous information networks, in Proc. 2019 IEEE/ACM Int. Conf. Advances in Social Networks Analysis and Mining, Vancouver, Canada, 2019, pp. 137–144.
[27]
C. Zhang, G. Wang, B. Yu, Y. Xie, and K. Pan, Proximity-aware heterogeneous information network embedding, Knowl. Based Syst., vol. 193, p. 105468, 2020.
Publication history
Copyright
Acknowledgements
Rights and permissions

Publication history

Received: 21 February 2023
Revised: 12 May 2023
Accepted: 15 May 2023
Published: 22 September 2023
Issue date: April 2024

Copyright

© The author(s) 2024.

Acknowledgements

This research was supported by the National Key Research and Development Program (No. 2019YFE0105300), the National Natural Science Foundation of China (No. 62103143), the Hunan Province Key Research and Development Program (No. 2022WK2006), the Special Project for the Construction of Innovative Provinces in Hunan (Nos. 2020TP2018 and 2019GK4030), and the Scientific Research Fund of Hunan Provincial Education Department (No. 22B0471).

Rights and permissions

The articles published in this open access journal are distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/).

Return