Abstract
Heterogeneous network representation learning shows its superior capacity in complex network analysis. It aims to embed nodes into a low-dimensional space and pursues a meaningful vector representation for each node. At present, the research of heterogeneous networks mainly focuses on the fusion of network structure information, semantic information, and attribute information. However, how to effectively extract neighboring structure information and accurately extract semantic information are still open problems. Furthermore, few people consider the difference between the importance of low-order structural information and high-order semantic information. In this paper, a multiple heterogeneous network representation learning framework based on multi-granularity information fusion called MHRL is proposed to solve these problems. MHRL considers the structural and semantic information of the heterogeneous network as different information grains, and uses different encoders to obtain structural and semantic embeddings. Then, MHRL uses a biased contrastive fusion method to effectively fuse structural embeddings and semantic embeddings. Extensive experiments on three real-world datasets show that the proposed method is significantly better than the state-of-the-art baselines in classification, clustering and visualization.
Similar content being viewed by others
Notes
References
Belghazi MID, Rajeswar S, Baratin A (2018) Mutual information neural estimation. In: The 35th international conference on machine learning
Cai H, Zheng VW, Chang CC (2018) A comprehensive survey of graph embedding: problems, techniques, and applications. IEEE Trans Knowl Data Eng 30(9):1616–1637
Cen Y, Zou X, Zhang J et al (2019) Representation learning for attributed multiplex heterogeneous network. ACM
Chen H, Yin H, Wang W et al (2018) PME: projected metric embedding on heterogeneous networks for link prediction. In: The 24th ACM SIGKDD international conference
Chen K, Wang G, Fu S et al (2022) MGRL: attributed multiplex heterogeneous network representation learning based on multi-granularity information fusion. Int J Mach Learn Cybern (1)
Chen T, Kornblith S, Norouzi M et al (2020) A simple framework for contrastive learning of visual representations[C]//International conference on machine learning. PMLR 1597–1607
Oord A, Li Y, Vinyals O (2018) Representation learning with contrastive predictive coding[J]. arXiv:1807.03748
Devlin J, Chang MW, Lee K et al (2019) Bert: pre-training of deep bidirectional transformers for language understanding. In: NAACL’2019
Dong Y, Chawla NV, Swami A (2017) metapath2vec: scalable representation learning for heterogeneous networks. In: The 23rd ACM SIGKDD international conference
Dong Y, Chawla NV, Swami A (2017) metapath2vec: scalable representation learning for heterogeneous networks. In: The 23rd ACM SIGKDD international conference on knowledge discovery and data mining
Fan S, Zhu J, Han X, et al (2019) Metapath-guided heterogeneous graph neural network for intent recommendation. In: The 25th ACM SIGKDD international conference
Feng Z, Xu C, Tao D (2019) Self-supervised representation learning by rotation feature decoupling. In: 2019 IEEE/CVF conference on computer vision and pattern recognition (CVPR)
Fu TY, Lee WC, Lei Z (2017) Hin2vec: explore meta-paths in heterogeneous information networks for representation learning. In: The 2017 ACM on conference on information and knowledge management
Hassani K, Khasahmadi AH (2020) Contrastive multi-view representation learning on graphs. In: The 37th international conference on machine learning
He K, Fan H, Wu Y et al (2020) Momentum contrast for unsupervised visual representation learning. In: 2020 IEEE/CVF conference on computer vision and pattern recognition (CVPR)
Hu B, Shi C, Zhao W (2018) Leveraging meta-path based context for top-n recommendation with a neural co-attention model. In: The 24th ACM SIGKDD international conference
Hu B, Fang Y, Shi C (2019) Adversarial learning on heterogeneous information networks. In: The 25th ACM SIGKDD conference on knowledge discovery and data mining
Huang X, Li J, Hu X (2017) Label informed attributed network embedding. In: The tenth ACM international conference
Jacob Y, Denoyer L, Gallinari P (2014) Learning latent representations of nodes for classifying in heterogeneous social networks. In: ACM, pp 373–382
Jaiswal A, Babu AR, Zadeh MZ et al (2020) A survey on contrastive self-supervised learning[J]. Technologies 9(1):2
Jin J, Qin J, Fang Y et al (2020) An efficient neighborhood-based interaction model for recommendation on heterogeneous graph. In: The 26th ACM sigkdd conference on knowledge discovery and data mining
Kalantidis Y, Sariyildiz MB, Pion N et al (2020) Hard negative mixing for contrastive learning. In: The 34th conference on neural information processing systems
Khosla M, Setty V, Anand A (2019) A comparative study for unsupervised network representation learning[J]. IEEE Transactions on Knowledge and Data Engineering 33(5):1807–1818
Lan Z, Chen M, Goodman S et al (2020) Albert: a lite bert for self-supervised learning of language representations. In: The 8th international conference on learning representations
Li J, Huang C, Qi J et al (2017) Three-way cognitive concept learning via multi-granularity. Inf Sci Int J 378:244–263
Liu X, Zhang F, Hou Z et al (2021) Self-supervised learning: generative or contrastive. IEEE Trans Knowl Data Eng (99):1–1
Park C, Kim D, Han J, et al. Unsupervised attributed multiplex network embedding[C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2020, 34(04): 5371–5378.
Park C, Kim D, Han J et al (2020) Unsupervised attributed multiplex network embedding. Proc AAAI Conf Artif Intell 34(4):5371–5378
Cui P, Wang X, Pei J et al (2018) A survey on network embedding[J]. IEEE transactions on knowledge and data engineering 31(5):833–852
Perozzi B, Al-Rfou R, Skiena S (2014) Deepwalk: online learning of social representations. In: The 20th ACM SIGKDD international conference on knowledge discovery and data mining
Ruan CY, Wang Y, Ma J et al (2019) Adversarial heterogeneous network embedding with metapath attention mechanism. J Comput Sci Technol 34(6):13
Shi C, Li Y, Zhang J et al (2016) A survey of heterogeneous information network analysis. IEEE Trans Knowl Data Eng 29(1):17–37
Shi C, Hu B, Zhao WX et al (2018) Heterogeneous information network embedding for recommendation[J]. IEEE Transact Know Data Eng 31(2):357–370
Sun Y, Barber R, Gupta M et al (2011) Co-author relationship prediction in heterogeneous bibliographic networks. In: International conference on advances in social networks analysis and mining
Sun Y, Han J, Yan X et al (2011) Pathsim: meta path-based top-k similarity search in heterogeneous information networks. Proc Vldb Endow 4(11):992–1003
Tang J, Qu M, Wang M et al (2015) Line: large-scale information network embedding. In: International conference on world wide web WWW
Tang J, Aggarwal C, Liu H (2016) Node classification in signed social networks. In: Proceedings of the 2016 SIAM international conference on data mining
Velikovi P, Fedus W, Hamilton WL (2019) Deep graph infomax. In: The 7th international conference on learning representations
Wang D, Cui P, Zhu W (2016) Structural deep network embedding. In: The 23nd ACM SIGKDD international conference on knowledge discovery and data mining
Wang G (2017) DGCC: data-driven granular cognitive computing[J]. Granular Computing 2(4):343–355
Wang G, Li S, Yang J (2018) A multi-granularity cognitive computing model bidirectionally driven by knowledge and data[J]. J Northwest University(Natural Science Edition) 48(4):488–500
Wang H, Zhang F, Hou M et al (2018) Shine: Signed heterogeneous information network embedding for sentiment link prediction. In: WSDM’2018
Wang X, Lu Y, Shi C et al (2020) Dynamic heterogeneous information network embedding with meta-path based proximity[J]. IEEE Transactions on Knowledge and Data Engineering Volume: 34(3):1117–1132
Wang X, Liu N, Han H, Shi C (2021) Self-supervised heterogeneous graph neural network with co-contrastive learning. In: The 27th ACM SIGKDD conference on knowledge discovery and data mining
Will Hamilton ZY, Leskovec J (2017) Inductive representation learning on large graphs. In: The 31st conference on neural information processing systems
Yang C, Xiao Y, Zhang Y, et al (2020) Heterogeneous network representation learning: Survey, benchmark, evaluation, and beyond[J]
Yonglong Tian DK, Isola P (2020) Contrastive multiview coding. In: The 16th European conference on computer vision
Zhang C, Song D, Huang C et al (2019) Heterogeneous graph neural network. In: The 25th ACM SIGKDD international conference on knowledge discovery and data mining
Zhang CQ, Hu J, Liu L et al (2019) Community detection based on joint representation of multi-granular networks. IEEE Access 7:177713–177722
Zhang F, Yuan NJ, Lian D (2016) Collaborative knowledge base embedding for recommender systems. In: The 22nd ACM SIGKDD conference on knowledge discovery and data mining
Zhao J, Wang X, Shi C et al (2020) Network schema preserving heterogeneous information network embedding. In: The 29th international joint conference on artificial intelligence and seventeenth pacific rim international conference on artificial intelligence IJCAI-PRICAI-20
Zhao Z, Chao L, Zhang X et al (2019) An incremental method to detect communities in dynamic evolving social networks. Knowl-Based Syst 163(JAN.1):404–415
Zhao J, Wang X, Shi C, Hu B, Song G, Ye Y (2021) Heterogeneous graph structure learning for graph neural networks. In: The 35th AAAI conference on artificial intelligence
Zheng J, Liu J, Shi C et al (2017) Recommendation in heterogeneous information network via dual similarity regularization. Int J Data Sci Anal 3(1):35–48
Acknowledgements
This work is supported by the National Natural Science Foundation of China under Grants 61936001 and 61772096, the Natural Science Foundation of Chongqing (cstc2019jcyj-cxttX0002, cstc2021ycjh-bgzxm0013), and the Key Cooperation Project of Chongqing Municipal Education Commission (HZ2021008).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Liu, M., Wang, G., Hu, J. et al. Multiple heterogeneous network representation learning based on multi-granularity fusion. Int. J. Mach. Learn. & Cyber. 14, 817–832 (2023). https://doi.org/10.1007/s13042-022-01665-w
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13042-022-01665-w