Skip to main content
SpringerLink
Log in

A Novel Deep Link Prediction Model for Peer-to-Peer Dynamic Task Collaboration Networks

  • Original Research
  • Published:
Peer-to-Peer Networking and Applications Aims and scope Submit manuscript

Abstract

In the dynamic and open peer-to-peer task collaboration scenarios, such as collaborative operations or post-earthquake coordinated rescue scenarios, the performance of personnel nodes or machine nodes will decrease with the consumption of energy, and the types of tasks that the nodes can perform change dynamically. Therefore, each node needs to dynamically maintain its immediate neighbors to guarantee the performance of task collaboration. In view of this, this paper pioneers the problem of directed link prediction for peer-to-peer dynamic task collaboration networks. First of all, the paper proposes two new link prediction metrics based on the link state change history, change time and multiple types of directed relationships between nodes. Secondly, based on the current feature vector and sequence feature vectors of related metrics between nodes, this paper reasonably designs the use mechanism of hybrid deep learning algorithms, and proposes a novel deep link prediction model. A large number of experiments have shown that the link prediction metrics we proposed are more suitable for the evolution of collaboration links under the dynamic peer-to-peer task collaboration environment, and the CFSF model achieves better prediction performance than other models.

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

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

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

Similar content being viewed by others

References

  1. Liben-Nowell D, Kleinberg J (2007) The link-prediction problem for social networks. J Am Soc Inform Sci Technol 58:1019–1031

    Article  Google Scholar 

  2. Wang H, Hu W, Qiu Z, Du B (2017) Nodes’ Evolution Diversity and Link Prediction in Social Networks. IEEE Trans Knowl Data Eng 29:2263–2274

    Article  Google Scholar 

  3. Wu S, Sun J, Tang J (2013) Patent partner recommendation in enterprise social networks, in Proc. sixth ACM international Conf. Web Search and Data Mining, Rome, Italy, pp. 43–52

  4. Bütün E, Kaya M et al (2020) Predicting Citation Count of Scientists as a Link Prediction Problem. IEEE Transactions on Cybernetics 50:4518–4529

    Article  Google Scholar 

  5. Kim M, Leskovec J (2011) The network completion problem: Inferring missing nodes and edges in networks, in Pro 2011 SIAM International Conf. Data Mining, Mesa, Arizona, USA, pp. 47–58

  6. Bringmann B, Berlingerio M, Bonchi F, Gionis A (2010) Learning and predicting the evolution of social networks. IEEE Intell Syst 25:26–35

    Article  Google Scholar 

  7. Zhu J, Hong J, Hughes JG (2002) Using Markov models for web site link prediction, in Pro. of the thirteenth ACM Conf. Hypertext and hypermedia, College Park, Maryland, USA, pp. 169–170

  8. Almansoori W, Gao S, Jarada TM, Alhajj R, Rokne J (2012) Link prediction and classification in social networks and its application in healthcare and systems biology, in Pro 2011 IEEE International Conf. Information Reuse and Integration, Las Vegas, NV, USA, pp. 422–428

  9. Wang P, Xu BW, Wu YR, Zhou XY (2015) Link prediction in social networks: the state-of-the-art, Science China. Inf Sci 58:1–38

    Google Scholar 

  10. De A, Bhattacharya S, Sarkar S, Ganguly N, Chakrabarti S (2016) Discriminative link prediction using local, community, and global signals. IEEE Trans Knowl Data Eng 28:2057–2070

    Article  Google Scholar 

  11. Zhu L, Guo D, Yin J, Ver Steeg G, Galstyan A (2016) Scalable temporal latent space inference for link prediction in dynamic social networks. IEEE Trans Knowl Data Eng 28:2765–2777

  12. Zhou T, Lü L, Zhang YC (2009) Predicting missing links via local information. Eur Phys J B 71:623–630

    Article  Google Scholar 

  13. Newman MEJ (2001) Clustering and preferential attachment in growing networks. Phys Rev E 64:1–16

    Google Scholar 

  14. Jaccard P (1901) Étude comparative de la distribution florale dans une portion des Alpes et des Jura. Bull Soc Vaudoise Sci Nat 37:547–579

    Google Scholar 

  15. Adamic LA, Adar E (2003) Friends and neighbors on the Web. Soc Networks 25:211–230

    Article  Google Scholar 

  16. Barabási AL, Albert R (1999) Emergence of scaling in random networks. Science 5439:509–512

    Article  MathSciNet  Google Scholar 

  17. Xu L, Wei X, Yu P, Cao J (2017) On learning mixed community-specific similarity metrics for cold-start link prediction, in Proc. International Conf. World Wide Web Companion, International World Wide Web Conferences Steering Committee, Perth, Australia, pp. 861–862

  18. Li J, Wu L, Cheng K, Liu H (2018) Streaming link prediction on dynamic attributed networks, in Pro. Eleventh ACM International Conf. Web Search and Data Mining, Marina Del Rey, CA, USA, pp. 369–377

  19. Arnoux T, Tabourier L, Latapy M (2017) Combining structural and dynamic information to predict activity in link streams, in Pro of the 2017 IEEE/ACM International Conf. Advances in Social Networks Analysis and Mining, Sydney, Australia, pp. 935–942

  20. Zhang M, Chen Y (2017) Weisfeiler-Lehman neural machine for link prediction, in Pro.ACM SIGKDD International Conf. Knowledge Discovery and Data Mining, Halifax, NS, Canada, pp.575–583

  21. Zhang L, Cheng H, Fang YQ (2018) CNN-based link representation and prediction method. Journal of Zhejiang University (Engineering Science) 52:552–559

    Google Scholar 

  22. Chen D, Yin S, Le J, Wang M, Pan Q (2017) A link prediction model for clinical temporal knowledge graph. Journal of Computer Research and Development 54:2920–2930

    Google Scholar 

  23. Liu B, Liu F, Wang X et al (2015) Link value of sequence behavior and prediction of event results in social networks, Science China: Information. Science 12:1558–1573

    Google Scholar 

  24. Fei GK, Musial-Gabrys K (2016) Hybrid structure-based link prediction model, in Pro. IEEE/ACM International Conf. Advances in Social Networks Analysis and Mining, San Francisco, CA, USA, pp. 1221–1228

  25. Shojafar M, Pooranian Z, Naranjo P et al (2017) FLAPS: bandwidth and delay-efficient distributed data searching in Fog-supported P2P content delivery networks. J Supercomput 73:5239–5260

    Article  Google Scholar 

  26. Bütün E, Kaya M, Alhajj R (2016) A new topological metric for link prediction in directed, weighted and temporal networks, in Pro. IEEE/ACM International Conf. Advances in Social Networks Analysis and Mining, San Francisco, CA, USA, pp. 954–959

  27. Sanz-Cruzado J, Pepa SM, Castells P, Novelty S (2018) Diversity in Link Prediction, in Proc the Web Conference 2018 Companion of the World Wide Web Conference. Lyon, France, pp 1347–1351

  28. Jeon H, Kim T (2017) Community-Adaptive Link Prediction, in Pro. International Conference on Data Mining, Communications and Information Technology, Phuket, Thailand, pp. 30

  29. Li J, Hu X, Jian L, Liu H (2017) Toward time-evolving feature selection on dynamic networks, in Pro IEEE International Conf Data Mining, New Orleans, LA, USA, pp. 1003–1008

  30. Jawed M, Kaya M, Alhajj R (2015) Time frame based link prediction in directed citation networks, in Pro 2015 IEEE/ACM International Conf Advances in Social Networks Analysis and Mining, Paris, France, pp. 1162–1168

  31. Luo H, Li L, Zhang Y et al (2021) Link prediction in multiplex networks using a novel multiple-attribute decision-making approach. Knowledge-Based Systems 219:106904

Download references

Author information

Authors and Affiliations

  1. Beijing Key Laboratory of Information Service Engineering, Beijing Union University, No.97 Beisihuan East Road, Chao Yang District, Beijing, 100101, China

    Danfeng Wu

  2. College of Robotics, Beijing Union University, No.4 Gongti North Road, Chaoyang District, Beijing, 100027, China

    Danfeng Wu & Jiancheng Zhang

  3. Beijing Engineering Research Center of Smart Mechanical Innovation Design Service, Beijing Union University, No.4 Gongti North Road, Chaoyang District, Beijing, 100027, China

    Jiancheng Zhang

  4. College of Mechanical Engineering, Guangxi University, No. 100 University East Road, Nanning, 530004, Guangxi, China

    Jinlai Zhang

  5. Department of Precision Instruments, Tsinhgua University, No.1 Qinghuayuan, Haidian District, Beijing, 100084, China

    Heng Shi

Authors
  1. Danfeng Wu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jiancheng Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Jinlai Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Heng Shi
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Jiancheng Zhang.

Ethics declarations

Conflict of interest

There are no conflicts of interest, and all authors unanimously agree to publish the paper and related research results of the paper.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Wu, D., Zhang, J., Zhang, J. et al. A Novel Deep Link Prediction Model for Peer-to-Peer Dynamic Task Collaboration Networks. Peer-to-Peer Netw. Appl. 15, 1775–1791 (2022). https://doi.org/10.1007/s12083-022-01324-5

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12083-022-01324-5

Keywords

Search

Navigation