Link prediction for heterogeneous information networks based on enhanced meta-path aggregation and attention mechanism | International Journal of Machine Learning and Cybernetics Skip to main content
Springer Nature Link
Log in

Link prediction for heterogeneous information networks based on enhanced meta-path aggregation and attention mechanism

  • Original Article
  • Published:
International Journal of Machine Learning and Cybernetics Aims and scope Submit manuscript

Abstract

Heterogeneous link prediction aims to reveal potential connections between two nodes in heterogeneous information networks. Most existing studies are based on meta-paths, but ignore the information contained in incomplete meta-paths. They simply aggregate meta-paths, leading to mining semantic information insufficiently. To solve this problem, we propose a link prediction model based on enhanced meta-path aggregation and attention mechanism. In this model, the deficiency of missing topological information from incomplete meta-paths is compensated by aggregating structural features and semantics. Different from existing meta-path encoders, we use recurrent neural networks and the attention mechanism to learn explicit and implicit semantic knowledge from meta-paths, which can capture more complex semantic associations between nodes. In addition, to avoid duplicate feature acquisition by random walking, we design a novel bidirectional biased random walking algorithm. It is applied to guide the generation of heterogeneous neighbors of each node that contain features ignored by the meta-path-wise model, which can mine complete topological information and get more accurate link prediction results. The extensive experiments on several datasets demonstrate that the proposed model outperforms baselines.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
¥17,985 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price includes VAT (Japan)

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

Data availability

Some or all data, models, or codes generated or used during the study are available from the corresponding author by request. They are also available in a repository or online.

References

  1. Hao P, Jianxin LI, Yangqiu S, Renyu Y, Ranjan R, Yu PS, Lifang HE (2021) Streaming social event detection and evolution discovery in heterogeneous information networks. ACM Trans Knowl Discov Data 15(5):1–33

    Article  Google Scholar 

  2. Alrabea A, Alzubi O, Alzubi J (2020) An enhanced mac protocol design o prolong sensor network lifetime. Int J Commun Antenna Propag (IRECAP) 10:37

    Article  Google Scholar 

  3. Babu MV, Alzubi JA, Sekaran R, Patan R, Ramachandran M, Gupta D (2021) An improved IDAF-FIT clustering based ASLPP-RR routing with secure data aggregation in wireless sensor network. Mob Netw Appl 26(3):1059–1067

    Article  Google Scholar 

  4. Pu C, Li J, Wang J, Quek TQS (2022) The node-similarity distribution of complex networks and its applications in link prediction. IEEE Trans Knowl Data Eng 34(8):4011–4023

    Article  Google Scholar 

  5. Ma G, Yan H, Qian Y, Wang L, Dang C, Zhao Z (2021) Path-based estimation for link prediction. Int J Mach Learn Cybern 12(9):2443–2458

    Article  Google Scholar 

  6. Yuan W, Han Y, Guan D, Han G, Tian Y, Al-Dhelaan A, Al-Dhelaan M (2022) Weighted enclosing subgraph-based link prediction for complex network. EURASIP J Wirel Commun Netw 2022(1):1–14

    Article  Google Scholar 

  7. Li C, Wei W, Feng X, Liu J (2021) Research of motif-based similarity for link prediction problem. IEEE Access 9:66636–66645

    Article  Google Scholar 

  8. Förster Y-P, Gamberi L, Tzanis E, Vivo P, Annibale A (2022) Exact and approximate mean first passage times on trees and other necklace structures: a local equilibrium approach. J Phys: Math Theor 55(11):1–33

    MathSciNet  MATH  Google Scholar 

  9. Shan N, Li L, Zhang Y, Bai S, Chen X (2020) Supervised link prediction in multiplex networks. Knowledge-Based Syst. https://doi.org/10.1016/j.knosys.2020.106168

    Article  Google Scholar 

  10. Zhu Z, Yan M, Deng X, Gao M (2022) Rating prediction of recommended item based on review deep learning and rating probability matrix factorization. Electron Commer Res Appl. https://doi.org/10.1016/j.elerap.2022.101160

    Article  Google Scholar 

  11. Gul H, Amin A, Adnan A, Huang K (2021) A systematic analysis of link prediction in complex network. IEEE Access 9:20531–20541

    Article  Google Scholar 

  12. Kumar S, Panda BS, Aggarwal D (2021) Community detection in complex networks using network embedding and gravitational search algorithm. J Intell Inf Syst 57(1):51–72

    Article  Google Scholar 

  13. Wang Z, Ye X, Wang C, Cui J, Yu PS (2021) Network embedding with completely-imbalanced labels. IEEE Trans Knowl Data Eng 33(11):3634–3647

    Article  Google Scholar 

  14. Zou J, Du Z, Zhao S (2022) Multi-granular attributed network representation learning. Int J Mach Learn Cybern 13(7):2071–2087

    Article  Google Scholar 

  15. Li H, Wang Y, Lyu Z, Shi J (2022) Multi-task learning for recommendation over heterogeneous information network. IEEE Trans Knowl Data Eng 34(2):789–802

    Article  Google Scholar 

  16. Raveendran AP, Alzubi JA, Sekaran R, Ramachandran M (2021) A high performance scalable fuzzy based modified asymmetric heterogene multiprocessor system on chip (AHt-MPSOC) reconfigurable architecture. J Intell Fuzzy Syst 42:1–12

    Google Scholar 

  17. Ruiz L, Gama F, Ribeiro A (2021) Graph neural networks: architectures, stability, and transferability. Proc IEEE 109(5):660–682

    Article  Google Scholar 

  18. Yang F, Zhang H, Tao S (2022) Hybrid deep graph convolutional networks. Int J Mach Learn Cybern 13(8):2239–2255

    Article  Google Scholar 

  19. Liang F, Qian C, Yu W, Griffith D, Golmie N (2022) Survey of graph neural networks and applications. Wirel Commun Mob Comput. https://doi.org/10.1155/2022/9261537

    Article  Google Scholar 

  20. Shengsheng Q, Jun HU, Quan F, Changsheng XU (2021) Knowledge-aware multi-modal adaptive graph convolutional networks for fake news detection. ACM Trans Multimed Comput Commun Appl 17(3):1–23

    Google Scholar 

  21. Zhang T, Shan H-R, Little MA (2022) Causal GraphSAGE: a robust graph method for classification based on causal sampling. Pattern Recognit 128:108696

    Article  Google Scholar 

  22. Mo X, Huang Z, Xing Y, Lv C (2022) Multi-agent trajectory prediction with heterogeneous edge-enhanced graph attention network. IEEE Trans Intell Transport Syst 23(7):9554–9567

    Article  Google Scholar 

  23. Fu X, Zhang J, Meng Z, King I (2020) MAGNN: metapath aggregated graph neural network for heterogeneous graph embedding. Proceedings of The Web Conference 2020. Association for Computing Machinery: Taipei, Taiwan, pp 2331–2341

    Chapter  Google Scholar 

  24. Zhang D, Yin J, Zhu X, Zhang C (2018) MetaGraph2Vec: complex semantic path augmented heterogeneous network embedding. Springer International Publishing, Cham, pp 196–208

    Google Scholar 

  25. Zhang C, Shang K-K, Qiao J (2021) Adaptive similarity function with structural features of network embedding for missing link prediction. Complexity. https://doi.org/10.1155/2021/1277579

    Article  Google Scholar 

  26. Zhou L-H, Wang J-L, Wang L-Z, Chen H-M, Kong B (2022) Heterogeneous information network representation learning: a survey. Jisuanji Xuebao/Chinese J Comput 45(1):160–189

    Google Scholar 

  27. Chen J, Huang F, Peng J (2021) MSGCN: multi-subgraph based heterogeneous graph convolution network embedding. Appl Sci (2076-3417) 11(21):9832

    Article  Google Scholar 

  28. Zheng S, Guan D, Yuan W (2022) Semantic-aware heterogeneous information network embedding with incompatible meta-paths. World Wide Web 25(1):1

    Article  Google Scholar 

  29. Banan A, Nasiri A, Taheri-Garavand A (2020) Deep learning-based appearance features extraction for automated carp species identification. Aquac Eng 89:102053

    Article  Google Scholar 

  30. Tang Z, Wang H, Yi X, Zhang Y, Kwong S, Kuo CJ (2023) Joint graph attention and asymmetric convolutional neural network for deep image compression. IEEE Trans Circuits Syst Video Technol 33(1):421–433

    Article  Google Scholar 

  31. Wang J, Zhao C, He S, Gu Y, Alfarraj O, Abugabah A (2022) LogUAD: log unsupervised anomaly detection based on word2Vec. Comput Syst Sci Eng 41(3):1207–1222

    Article  Google Scholar 

  32. Mei J, Wang Y, Tu X, Dong M, He T (2023) Incorporating BERT with probability-aware gate for spoken language understanding. IEEE/ACM Trans Audio Speech Lang Process 31:826–834

    Article  Google Scholar 

  33. Li RQ, Zhao X, Moens MF (2023) A brief overview of universal sentence representation methods: a linguistic view. Acm Comput Surv 55(3):1

    Google Scholar 

  34. Weibin C, Danial S, Guoxi L, Shahab SB, Kwok Wing C, Amir M (2022) Accurate discharge coefficient prediction of streamlined weirs by coupling linear regression and deep convolutional gated recurrent unit. Eng Appl Comput Fluid Mech 16(1):965–976

    Google Scholar 

  35. Wang W-C, Du Y-J, Chau K-W, Xu D-M, Liu C-J, Ma Q (2021) An ensemble hybrid forecasting model for annual runoff based on sample entropy, secondary decomposition, and long short-term memory neural network. Water Resour Manag 35(14):4695–4726

    Article  Google Scholar 

  36. Alzubi JA, Jain R, Kathuria A, Khandelwal A, Saxena A, Singh A (2020) Paraphrase identification using collaborative adversarial networks. J Intell Fuzzy Syst 39(1):1021–1032

    Article  Google Scholar 

  37. Wei H, Zhou A, Zhang Y, Chen F, Qu W, Lu M (2022) Biomedical event trigger extraction based on multi-layer residual BiLSTM and contextualized word representations. Int J Mach Learn Cybern 13(3):721–733

    Article  Google Scholar 

  38. Fan Y, Xu K, Wu H, Zheng Y, Tao B (2020) Spatiotemporal modeling for nonlinear distributed thermal processes based on KL decomposition, MLP and LSTM network. IEEE Access 8:25111–25121

    Article  Google Scholar 

  39. Chengcheng C, Qian Z, Mahsa HK, Changhyun J, Sayed MB, Shahab SB, Sonam Sandeep D, Kwok-Wing C (2022) Forecast of rainfall distribution based on fixed sliding window long short-term memory. Eng Appl Comput Fluid Mech 16(1):248–261

    Google Scholar 

  40. Wang J, Li H, Liang L, Zhou Y (2022) Community discovery algorithm of complex network attention model. Int J Mach Learn Cybern 13(6):1619–1631

    Article  Google Scholar 

  41. Kazemi B, Abhari A (2020) Content-based Node2Vec for representation of papers in the scientific literature. Data Knowl Eng 127:101794

    Article  Google Scholar 

  42. Baptista A, Gonzalez A, Baudot A (2022) Universal multilayer network exploration by random walk with restart. Commun Phys 5(1):1–9

    Article  Google Scholar 

  43. Jiang J-Y, Li Z, Ju CJT, Wang W (2020) In MARU: Meta-context Aware Random Walks for Heterogeneous Network Representation Learning, 29th ACM International Conference on Information and Knowledge Management, CIKM 2020, October 19, 2020 - October 23, 2020, Virtual, Online, Ireland, Association for Computing Machinery: Virtual, Online, Ireland, pp. 575–584.

  44. Xu L, He Z, Wang K, Wang C, Huang S (2022) Explicit message-passing heterogeneous graph neural network. IEEE Trans Knowl Data Eng 99:1–13

    Google Scholar 

  45. Haitham AA, Ahmedbahaaaldin IAO, Yusuf E, Ali NA, Yuk FH, Ozgur K, Mohsen S, Ahmed S, Kwok-wing C, Ahmed E-S (2021) Modeling the fluctuations of groundwater level by employing ensemble deep learning techniques. Eng Appl Comput Fluid Mech 15(1):1420–1439

    Google Scholar 

  46. Zeng K, Liu J, Jiang Z, Xu D (2022) A decreasing scaling transition scheme from Adam to SGD. Adv Theory Simul 5(7):1–10

    Article  Google Scholar 

  47. Cai L, Li J, Wang J, Ji S (2022) Line graph neural networks for link prediction. IEEE Trans Pattern Anal Mach Intell 44(9):5103–5113

    Google Scholar 

  48. Singh SS, Mishra S, Kumar A, Biswas B (2022) Link prediction on social networks based on centrality measures. Springer Sci Bus Media Deutschland GmbH 246:71–89

    Google Scholar 

Download references

Funding

National Science Foundation of China, 61602491, Lunwen Wang.

Author information

Authors and Affiliations

  1. College of Electronic Engineering, National University of Defense Technology, Hefei, 230031, China

    Hao Shao, Lunwen Wang & Rangang Zhu

Authors
  1. Hao Shao
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Lunwen Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Rangang Zhu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Lunwen Wang.

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.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Shao, H., Wang, L. & Zhu, R. Link prediction for heterogeneous information networks based on enhanced meta-path aggregation and attention mechanism. Int. J. Mach. Learn. & Cyber. 14, 3087–3103 (2023). https://doi.org/10.1007/s13042-023-01822-9

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s13042-023-01822-9

Keywords

Search

Navigation