Abstract
Multiview learning has caught the interest of many graph researchers because it can learn richer information about graphs from different views. Recently, multiview learning, as a novel paradigm in learning, has been widely applied to learn nodes representation of heterogeneous graphs, such as MVSE, HeMI, etc., they only utilize the local homogeneous neighborhood information of nodes, which degrades the quality of nodes representation. We are aware that the heterogeneous graph representation aims to drive the representation of a node to be near the homogeneous neighbors that are similar to it in the heterogeneous graph and far wary from heterogeneous neighbors. Besides, in the heterogeneous graph, linked nodes are more likely to be dissimilar, but remote nodes may have some similarities. Therefore, we can move the locality of a node to discover more homogenous neighbors’ information to improve the quality of node representation. In this work, we propose an unsupervised heterogeneous graph embedding technique that is simple yet efficient; and devise a systematic way to learn node embeddings from the local and global views of the homogeneous neighborhood of nodes by introducing a regularization framework that minimizes the disagreements among the local and global node embeddings under the specific meta-path. Inspired by Personal PageRank graph diffusion, we expand an infinite meta path-based restart random walk to obtain global homogenous neighbors of nodes and construct a meta path-based diffusion matrix to represent the relation between global homogenous neighbors and nodes. Finally, we employ mini-batch gradient descent to train our model to reduce computational consumption. Experimental findings demonstrate that our approach outperforms a wide variety of baselines on different datasets when it comes to node classification and node clustering tasks, with a particularly impressive 7.22% improvement over the best baseline on the ACM dataset.
Similar content being viewed by others
Data availability and access
Data is available on request from the authors.
References
Li K, Ye W (2022) Semi-supervised node classification via graph learning convolutional neural network. Appl Intell 52:12724–12736. https://doi.org/10.1007/s10489-022-03233-9
Zhang M, Chen Y (2018) Link prediction based on graph neural networks. In: Proceedings of the 32nd International Conference on Neural Information Processing Systems, pp 5171-5181
Lu X, Wang L, Jiang Z et al (2022) MMKRL: A robust embedding approach for multi-modal knowledge graph representation learning. Appl Intell 52:7480–7497. https://doi.org/10.1007/s10489-021-02693-9
Wang M, Lin Y, Lin G, Yang K, Wu X (2020) M2grl: A multi-task multi-view graph representation learning framework for web-scale recommender systems. In: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery and Data Ming, pp 2349-2358
Hamilton W, Ying R, Leskovec J (2017) Inductive representation learning on large graphs. In: Proceedings of the 31nd International Conference on Neural Information Processing Systems, pp 1025-1035
Kipf T N, Welling M (2017) Semi-supervised classification with graph convolutional networks. In: International Conference on Learning Representations
Petar V, Guillem C, Arantxa C, Adriana R, Pietro L et al (2018) Graph Attention Networks. In: International Conference on Learning Representations
Jiani Z, Xingjian S, Junyuan X, Hao M et al (2018) GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphs. In: 34th Conference on Uncertainty in Artificial Intelligence, pp 339-349
Zhang J, Shi X, Zhao S, King I (2019) STAR-GCN: Stacked and Reconstructed Graph Convolutional Networks for Recommender Systems. In: International Joint Conference on Artificial Intelligence, pp 4264-4270
Michael S, Kipf T N, Bloem P et al (2018) Modeling relational data with graph convolutional networks. In: Extended Semantic Web Conference
Zhang C, Song D, Huang C, Ananthram S et al (2019) Heterogeneous graph neural network. In: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Ming, pp 793-803
Qin X, Nasrullah S, Berthold R, Lingfei W (2021) Relation-aware graph attention model with adaptive self-adversarial training. In: Proceedings of the AAAI conference on artificial intelligence
Hu Z, Dong Y, Wang K, Sun Y (2020) Heterogeneous graph transformer. Proc Web Conf 2020:2704–2710
Wang X, Ji H, Shi C, Wang B et al (2019) Heterogeneous graph attention network. In: Proceedings of The Web Conference 2019
Fu X, Zhang J, Meng Z, King I (2020) Magnn: Metapath aggregated graph neural network for heterogeneous graph embedding. Proc Web Conf 2020:2331–2341
Zhong Q, Liu Y, Ao X, Hu B et al (2020) Financial defaulter detection on online credit payment via multi-view attributed heterogeneous information network. Proc Web Conf 2020:785–795
Xie F, Cao Z, Xu Y, Chen L, Zheng Z (2020) Graph neural network and multi-view learning based mobile application recommendation in heterogeneous graphs. In: 2020 IEEE International Conference on Services Computing, pp 100-107
Fan S, Zhu J, Han X, Shi C et al (2019) Metapath guided heterogeneous graph neural network for intent recommendation. In: Proceedings of the 25th SIGKDD, pp 2478-2486
Xu F, Lian J, Han Z, Li Y et al (2019) Relation aware graph convolutional networks for agent-initiated social eCommerce recommendation. In: Proceedings of the 28th CIKM, pp 529-538
Ji H, Zhu J, Wang X, Shi C et al (2021) Who you would like to share with? a study of share recommendation in social e-commerce. In: Proceedings of the AAAI conference on artificial intelligence
Zhao J, Wen Q, Sun S, Ye Y et al (2021) Multi-View Self-Supervised Heterogeneous Graph Embedding. European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, pp 319-334
Wang X, Liu N, Han H, Shi C (2021) Self-supervised Heterogeneous Graph Neural Network with Co-contrastive Learning. In: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, https://doi.org/10.1145/3447548.3467415
Yang C, Xiao Y, Zhang Y, Sun Y, Han J (2020) Heterogeneous network representation learning: a unified framework with survey and benchmark. In: IEEE Transactions on Knowledge and Data Engineering, pp 4854-4873
Dong Y, Chawla N V, Swami A: (2017) metapath2vec: scalable representation learning for heterogeneous networks. In: KDD, pp 135-144
He Y, Song Y, Li J, Ji C, et al (2019) HeteSpaceyWalk: a heterogeneous spacey random walk for heterogeneous information network embedding. In: CIKM, pp 639-648
Hussein R, Yang D, Cudr’e-Mauroux P (2018) Are meta-paths necessary? Revisiting heterogeneous graph embeddings. In: CIKM, pp 437-446
Zhang C, Swami A, Chawla N V (2019) SHNE: representation learning for semantic associated heterogeneous networks. In: WSDM, pp 690-698
Lu Y, Shi C, Hu L, Liu Z (2019) Relation structure-aware heterogeneous information network embedding. In: AAAI, pp 4456-4463
Hu B, Zhang Z, Shi C, Zhou J et al (2019) Cash-out user detection based on attributed heterogeneous information network with a hierarchical attention mechanism. In: AAAI, pp 946-953
Hu L, Yang T, Shi C, Ji H et al (2019) Heterogeneous graph attention networks for semi-supervised short text classification. In: EMNLP-IJCNLP, pp 4820-4829
Li A, Qin Z, Liu R, Yang Y, Li D (2019) Spam review detection with graph convolutional networks. In: CIKM, pp 2703-2711
Teng SH (2016) Scalable algorithms for data and network analysis. Foundations and Trends in Theoretical Computer Science, pp 1–274
Hong H, Guo H, Lin Y, Yang X et al (2020) An attention-based graph neural network for heterogeneous structural learning. In: AAAI, pp 4132-4139
Zhao J, Wang X, Shi C, Liu Z et al (2020) Network schema preserving heterogeneous information network embedding. In: IJCAI, pp 1366-1372
Yun S, Jeong M, Kim R, Kang J, Kim H J (2019) Graph transformer networks. In: NIPS, pp 11960-11970. 49. Zhao K, et al (2020) Deep adversarial completion for sparse heterogeneous information network embedding. In: WWW, pp 508-518
Ren Y, Liu B, Huang C, Dai P, et al (2019) Heterogeneous Deep Graph Infomax. arXiv:1911.08538
Lee S H, Feng J, and Tay W P (2021) Learning on heterogeneous graphs using high-order relations. In: EEE International Conference on Acoustics, Speech and Signal Processing
Teng SH et al (2016) Scalable algorithms for data and network analysis. Found Trend Theor Comput Sci 12(1–2):1–274
Sebastian N, Botond C, Ryota T (2016) F-GAN: Training Generative Neural Samplers using Variational Divergence Minimization. In: Proceedings of the 30th International Conference on Neural Information Processing Systems, pp 271-279
Zhu D, Sun Y, Du H, Tian Z (2022) MHNF: Multi-hop Heterogeneous Neighborhood information Fusion graph representation learning. In: IEEE Transactions on Knowledge and Data Engineering, pp 1-14, https://doi.org/10.1109/TKDE.2022.3186158
Chanyoung P, Donghyun K, Jiawei H, Hwanjo Y (2020) Unsupervised Attributed Multiplex Network Embedding. In AAAI, pp 5371-5378
Ni L, William WC (2010) Relational retrieval using a combination of path-constrained random walks. Machine Learning, pp 53-67
Garcez, d’Avila AS, Krysia B, Dov MG (2001) Symbolic knowledge extraction from trained neural networks: A sound approach. Artificial Intelligence, pp 155-207
Liu Z, Qian P, Wang X, Zhuang Y et al (2023) Combining Graph Neural Networks With Expert Knowledge for Smart Contract Vulnerability Detection. In: IEEE Transactions on Knowledge and Data Engineering, pp 1296-1310, https://doi.org/10.1109/TKDE.2021.3095196
Xu K, Li C, Tian Y, Sonobe T, Jegelka S (2018) Representation Learning on Graphs with Jumping Knowledge Networks. ICML
Shi C, Hu B, Zhao WX, Philip SY (2018) Heterogeneous information network embedding for recommendation. IEEE Trans. Knowl. Data Eng. 31(2):357–370
Tang J, Qu M, Mei Q (2015) Pte: Predictive text embedding through large-scale heterogeneous text networks. In: Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. pp 1165-1174
Chang S, Han W, Tang J, Qi GJ, Aggarwal CC, Huang TS (2015) Heterogeneous network embedding via deep architectures. In: Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp 119-128
Acknowledgements
This work was supported by the Natural Science Foundation of Guangdong Province (Grant Nos. 2020A1515010696 ), and the Science and Technology Program of Guangzhou City (Grant Nos. 201707010052). And we also thank Ningsi Li, because he proposes constructive suggestions and participates in the revision of the article.
Author information
Authors and Affiliations
Contributions
Dongjie Li has made substantial contributions to the conception or design of the work, or acquisition, analysis, or interpretation of data for the work, and has drafted the work or revised it critically for important intellectual content. Dong Li has approved the final version. Hao Liu checks the final version.
Corresponding author
Ethics declarations
Conflicts of interest
All of us here attest that there are no competing interests with this study.
Ethical and informed consent for data used
Ethical and informed consent for data used.
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 (e.g. a society or other partner) 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
Li, D., Li, D. & Liu, H. Multiview learning of homogeneous neighborhood of nodes for the node representation of heterogeneous graph. Appl Intell 53, 25184–25200 (2023). https://doi.org/10.1007/s10489-023-04907-8
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-023-04907-8