Wide & Deep Learning in Job Recommendation: An Empirical Study

  • Shaoyun Shi
  • Min ZhangEmail author
  • Hongyu Lu
  • Yiqun Liu
  • Shaopin Ma
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10648)


Recommender systems have become more and more popular in recent years. Collaborative Filtering and Content-Based methods are widely used for a long time. Recently, some researchers introduced deep learning algorithms into recommender system. In this paper, we try to answer some questions about a novel recommender model, Wide & Deep Learning. Firstly, how should we select and feed in features? Secondly, how does Wide & Deep Learning work? Thirdly, how to joint-train the two parts of the network? Finally, how to conduct online training with new data? For all of these, we focus on the job recommendation task, which often suffers from the cold-start problem. The experiments give us the answers of these questions.


Recommender system Wide & Deep Learning Job recommendation 


  1. 1.
    Sweeney, L.: Confidentiality, disclosure, and data access: theory and practical applications for statistical agencies. Inform. Explosion, 43–74 (2001)Google Scholar
  2. 2.
    LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436–444 (2015)CrossRefGoogle Scholar
  3. 3.
    He, K., Zhang, X., Ren, S., et al.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)Google Scholar
  4. 4.
    Manning, C., Socher, R., Fang, G.G., et al.: CS224n: natural language processing with deep learning1 (2017)Google Scholar
  5. 5.
    Son, L.H.: Dealing with the new user cold-start problem in recommender systems: a comparative review. Inform. Syst. 58, 87–104 (2016)CrossRefGoogle Scholar
  6. 6.
    Cheng, H.T., Koc, L., Harmsen, J., et al.: Wide & deep learning for recommender systems. In: Proceedings of the 1st Workshop on Deep Learning for Recommender Systems, pp. 7–10. ACM (2016)Google Scholar
  7. 7.
    Pan, R., Zhou, Y., Cao, B., et al.: One-class collaborative filtering. In: Eighth IEEE International Conference on Data Mining, ICDM 2008, pp. 502–511. IEEE (2008)Google Scholar
  8. 8.
    Liang, D., Charlin, L., McInerney, J., et al.: Modeling user exposure in recommendation. In: Proceedings of the 25th International Conference on World Wide Web. International World Wide Web Conferences Steering Committee, pp. 951–961 (2016)Google Scholar
  9. 9.
    Weimer, M., Karatzoglou, A., Smola, A.: Improving maximum margin matrix factorization. Mach. Learn. 72(3), 263–276 (2008)CrossRefGoogle Scholar
  10. 10.
    Rendle, S., Freudenthaler, C., Gantner, Z., et al.: BPR: Bayesian personalized ranking from implicit feedback. In: Proceedings of the Twenty-Fifth Conference on Uncertainty in Artificial Intelligence, pp. 452–461. AUAI Press (2009)Google Scholar
  11. 11.
    Lops, P., De Gemmis, M., Semeraro, G.: Content-based recommender systems: state of the art and trends. In: Ricci, F., Rokach, L., Shapira, B., Kantor, P. (eds.) Recommender Systems Handbook. Springer, Boston (2011). doi: 10.1007/978-0-387-85820-3_3 Google Scholar
  12. 12.
    Van den Oord, A., Dieleman, S., Schrauwen, B.: Deep content-based music recommendation. In: Advances in Neural Information Processing Systems, pp. 2643–2651 (2013)Google Scholar
  13. 13.
    Li, S., Kawale, J., Fu, Y.: Deep collaborative filtering via marginalized denoising auto-encoder. In: Proceedings of the 24th ACM International on Conference on Information and Knowledge Management [S.l.], pp. 811–820. ACM (2015)Google Scholar
  14. 14.
    He, X., Liao, L., Zhang, H., et al.: Neural collaborative filtering. In: Proceedings of the 26th International Conference on World Wide Web. International World Wide Web Conferences Steering Committee, pp. 173–182 (2017)Google Scholar
  15. 15.
    Zheng, Y., Tang, B., Ding, W., et al.: A neural autoregressive approach to collaborative filtering. arXiv preprint arXiv:1605.09477 (2016)
  16. 16.
    Zheng, Y., Liu, C., Tang, B., et al.: Neural autoregressive Collaborative Filtering for implicit feedback. In: Proceedings of the 1st Workshop on Deep Learning for Recommender Systems [S.l.], pp. 2–6. ACM, 2016Google Scholar
  17. 17.
    Kingma, D., Adam, B.J.: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
  18. 18.
    Deng, L.Y.: The cross-entropy method: a unified approach to combinatorial optimization. Monte-Carlo Simul. Mach. Learn. (2006)Google Scholar
  19. 19.
    Bach, S., Binder, A., Montavon, G., et al.: On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation. PloS One 10(7), e0130140 (2015)CrossRefGoogle Scholar
  20. 20.
    Binder, A., Bach, S., Montavon, G., Müller, K.-R., Samek, W.: Layer-wise relevance propagation for deep neural network architectures. Information Science and Applications (ICISA) 2016. LNEE, vol. 376, pp. 913–922. Springer, Singapore (2016). doi: 10.1007/978-981-10-0557-2_87 CrossRefGoogle Scholar
  21. 21.
    Ding, Y., Liu, Y., Luan, H., et al.: Visualizing and understanding neural machine translationGoogle Scholar
  22. 22.
    Arras, L., Montavon, G., Müller, K.R., et al.: Explaining recurrent neural network predictions in sentiment analysis. arXiv preprint arXiv:1706.07206 (2017)
  23. 23.
    Dai, H., Wang, Y., Trivedi, R., et al.: Recurrent coevolutionary feature embedding processes for recommendation. arXiv preprint arXiv:1609.03675 (2016)

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Shaoyun Shi
    • 1
  • Min Zhang
    • 1
    Email author
  • Hongyu Lu
    • 1
  • Yiqun Liu
    • 1
  • Shaopin Ma
    • 1
  1. 1.Tsinghua National Laboratory for Information Science and Technology, Department of Computer Science and TechnologyTsinghua UniversityBeijingChina

Personalised recommendations