PRTNets: Cold-Start Recommendations Using Pairwise Ranking and Transfer Networks

  • Dylan M. Valerio
  • Prospero C. NavalJr.Email author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12033)


In collaborative filtering, matrix factorization, which decomposes the ratings matrix into low rank user and item latent matrices is widely used. The decomposition is based on the rating scores of users to item, with the user and item latent matrices sharing a common embedding space. A similarity function between the two represents the predicted rating of a user to an item. However, this matrix factorization approach falls short for cold-start recommendation where items have very few or no ratings. This paper puts forward a novel approach of doing cold-start recommendation by using a neural network, the Transfer Network, to learn a nonlinear mapping from item features to the item latent matrix. The item latent matrix is produced by another network, the Pairwise Ranking Network, which utilizes pairwise ranking functions. The Pairwise Ranking Network efficiently utilizes implicit feedback by optimizing the ranking of the recommendation list. We find the optimal architecture for the Pairwise Network and the Transfer Network through warm-start and cold-start evaluation. With the Transfer Network, we map the Tag Genome dataset to the item latent matrix and produce cold-start recommendations for a test set derived from the MovieLens 20M dataset. Our approach yielded a significant margin of improvement of 0.276 and 0.089 average precision at \(k=10\) over the baseline LightFM and neighborhood averaging methods respectively.


Machine learning Recommender systems Neural networks Transfer learning 


  1. 1.
    Gantner, Z., Drumond, L., Freudenthaler, C., Rendle, S., Schmidt-Thieme, L.: Learning attribute-to-feature mappings for cold-start recommendations. In: Proceedings of the IEEE International Conference on Data Mining (ICDM), pp. 176–185 (2010).
  2. 2.
    Harper, F.M., Konstan, J.A.: The MovieLens datasets: history and context. ACM Trans. Interact. Intell. Syst. 5(4), 19:1–19:19 (2015). CrossRefGoogle Scholar
  3. 3.
    Hinton, G.E., Srivastava, N., Swersky, K.: Lecture 6a- overview of mini-batch gradient descent. In: COURSERA: Neural Networks for Machine Learning, p. 31 (2012).
  4. 4.
    Hu, Y., Koren, Y., Volinsky, C.: Collaborative filtering for implicit feedback. In: IEEE International Conference on Data Mining, pp. 263–272 (2008).
  5. 5.
    Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift (2015).
  6. 6.
    Koren, Y.: The BellKor solution to the Netflix grand prize. Netflix prize documentation, 1–10 August 2009.
  7. 7.
    Kula, M.: Metadata embeddings for user and item cold-start recommendations. In: CEUR Workshop Proceedings (2015)Google Scholar
  8. 8.
    Liu, K., Natarajan, P.: WMRB: learning to rank in a scalable batch training approach (2017)Google Scholar
  9. 9.
    van den Oord, A., Dieleman, S., Schrauwen, B.: Deep content-based music recommendation. In: Electronics and Information Systems department (ELIS), p. 9 (2013).
  10. 10.
    Rendle, S.: Factorization machines. In: Proceedings of the 2010 IEEE International Conference on Data Mining (ICDM 2010), pp. 995–1000. IEEE Computer Society, Washington, DC (2010).
  11. 11.
    Rendle, S., Freudenthaler, C., Gantner, Z., Schmidt-Thieme, L.: BPR: Bayesian personalized ranking from implicit feedback (2012)Google Scholar
  12. 12.
    Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15, 1929–1958 (2014)MathSciNetzbMATHGoogle Scholar
  13. 13.
    Takács, G.: Alternating least squares for personalized ranking (2012).
  14. 14.
    Vig, J., Riedl, J.: The tag genome: encoding community knowledge to support novel interaction. ACM Trans. Interact. Intell. Syst. 2(44) (2012).
  15. 15.
    Weston, J., Bengio, S., Usunier, N.: WSABIE: scaling up to large vocabulary image annotation (2011)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Computer Vision and Machine Intelligence Group, Department of Computer ScienceUniversity of the PhilippinesQuezon CityPhilippines

Personalised recommendations