Skip to main content

An Efficient Manifold Density Estimator for All Recommendation Systems

  • Conference paper
  • First Online:
Neural Information Processing (ICONIP 2021)

Abstract

Most current neural recommender systems for session-based data cast recommendations as a sequential or graph traversal problem, applying recurrent networks (LSTM/GRU) or graph neural networks (GNN). This makes the systems increasingly elaborate in order to model complex user/item connection networks and results in poor scalability to large item spaces and long item view/click sequences. Instead on focusing on the sequential nature of session-based recommendation, we propose to cast it as a density estimation problem on item sets. We introduce EMDE (Efficient Manifold Density Estimator) - a method utilizing arbitrary vector representations with the property of local similarity to succinctly represent smooth probability densities on Riemannian manifolds using compressed representations we call sketches. Within EMDE, session behaviors are represented with weighted item sets, largely simplifying the sequential aspect of the problem. Applying EMDE to both top-k and session-based recommendation settings, we establish new state-of-the-art results on multiple open datasets in both uni-modal and multi-modal settings. EMDE has also been applied to many other tasks and areas in top machine learning competitions involving recommendations and graph processing, taking the podium in KDD Cup 2021, WSDM Challenge 2021, and SIGIR eCom Challenge 2020. We release the code at https://github.com/emde-conf/emde-session-rec.

J. Dąbrowski and B. Rychalska—Equal contribution.

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

Access this chapter

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

Notes

  1. 1.

    https://github.com/rn5l/session-rec.

  2. 2.

    Standard configuration recommended by [16].

References

  1. Backurs, A., Indyk, P., Wagner, T.: Space and time efficient kernel density estimation in high dimensions. In: NeurIPS (2019)

    Google Scholar 

  2. Ben-Shimon, D., Tsikinovsky, A., Friedmann, M., Shapira, B., Rokach, L., Hoerle, J.: Recsys challenge 2015 and the yoochoose dataset. In: RecSys (2015)

    Google Scholar 

  3. Bennett, J., Lanning, S., Netflix, N.: The netflix prize. In: In KDD Cup and Workshop in Conjunction with KDD (2007)

    Google Scholar 

  4. Charikar, M., Siminelakis, P.: Hashing-based-estimators for kernel density in high dimensions. In: 2017 IEEE 58th Annual Symposium on Foundations of Computer Science (FOCS) (2017)

    Google Scholar 

  5. Chen, T., Wong, R.C.W.: Handling information loss of graph neural networks for session-based recommendation (2020)

    Google Scholar 

  6. Coleman, B., Shrivastava, A.: Sub-linear race sketches for approximate kernel density estimation on streaming data, pp. 1739–1749, April 2020

    Google Scholar 

  7. Coleman, B., Shrivastava, A., Baraniuk, R.G.: Race: sub-linear memory sketches for approximate near-neighbor search on streaming data (2019)

    Google Scholar 

  8. Cormode, G., Muthukrishnan, S.: An improved data stream summary: the count-min sketch and its applications. In: Farach-Colton, M. (ed.) LATIN 2004: Theoretical Informatics (2004)

    Google Scholar 

  9. Dacrema, M.F., Cremonesi, P., Jannach, D.: Are we really making much progress? a worrying analysis of recent neural recommendation approaches. In: RecSys (2019)

    Google Scholar 

  10. Dognin, P., Melnyk, I., Mroueh, Y., Ross, J., Santos, C.D., Sercu, T.: Wasserstein barycenter model ensembling (2019)

    Google Scholar 

  11. Greengard, L., Strain, J.: The fast gauss transform (1991)

    Google Scholar 

  12. Hidasi, B., Karatzoglou, A.: Recurrent neural networks with top-k gains for session-based recommendations. In: CIKM (2018)

    Google Scholar 

  13. Indyk, P., Motwani, R.: Approximate nearest neighbors: towards removing the curse of dimensionality. In: Conference Proceedings of the Annual ACM Symposium on Theory of Computing (2000)

    Google Scholar 

  14. Itoh, M., Satoh, H.: Geometric mean of probability measures and geodesics of fisher information metric (2017)

    Google Scholar 

  15. Kamehkhosh, I., Jannach, D., Ludewig, M.: A comparison of frequent pattern techniques and a deep learning method for session-based recommendation. In: RecTemp@RecSys (2017)

    Google Scholar 

  16. Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: Bengio, Y., LeCun, Y. (eds.) ICLR (20150

    Google Scholar 

  17. LeCun, Y., Cortes, C.: MNIST handwritten digit database (2010). http://yann.lecun.com/exdb/mnist/

  18. Li, J., Ren, P., Chen, Z., Ren, Z., Lian, T., Ma, J.: Neural attentive session-based recommendation. In: Proceedings of the 2017 ACM on Conference on Information and Knowledge Management, CIKM 2017. Association for Computing Machinery, New York (2017)

    Google Scholar 

  19. Liang, D., Krishnan, R.G., Hoffman, M.D., Jebara, T.: Variational autoencoders for collaborative filtering. In: WWW (2018)

    Google Scholar 

  20. Liu, Q., Zeng, Y., Mokhosi, R., Zhang, H.: Stamp: short-term attention/memory priority model for session-based recommendation. In: KDD (2018)

    Google Scholar 

  21. Ludewig, M., Jannach, D.: Evaluation of session-based recommendation algorithms. User Model. User-Adap. Inter. 28(4–5), 331–390 (2018)

    Article  Google Scholar 

  22. Ludewig, M., Mauro, N., Latifi, S., Jannach, D.: Performance comparison of neural and non-neural approaches to session-based recommendation. In: RecSys (2019)

    Google Scholar 

  23. Mi, F., Faltings, B.: Context tree for adaptive session-based recommendation. http://arxiv.org/abs/1806.03733

  24. Ning, X., Karypis, G.: Slim: sparse linear methods for top-n recommender systems. In: ICDM (2011)

    Google Scholar 

  25. Paudel, B., Christoffel, F., Newell, C., Bernstein, A.: Updatable, accurate, diverse, and scalable recommendations for interactive applications. ACM Trans. Interact. Intell, Syst 7, 1–34 (2016)

    Google Scholar 

  26. Pennington, J., Socher, R., Manning, C.D.: Glove: global vectors for word representation. In: Empirical Methods in Natural Language Processing (EMNLP) (2014)

    Google Scholar 

  27. Ruocco, M., Skrede, O.S.L., Langseth, H.: Inter-session modeling for session-based recommendation. In: DLRS (2017)

    Google Scholar 

  28. Rychalska, B., Bąbel, P., Gołuchowski, K., Michałowski, A., Dabrowski, J.: Cleora: a simple, strong and scalable graph embedding scheme. arXiv https://arxiv.org/abs/2102.02302 (2020)

  29. Siminelakis, P., Rong, K., Bailis, P., Charikar, M., Levis, P.: Rehashing kernel evaluation in high dimensions. In: International Conference on Machine Learning (2019)

    Google Scholar 

  30. Steck, H.: Embarrassingly shallow autoencoders for sparse data. In: WWW (2019)

    Google Scholar 

  31. Tallec, C., Ollivier, Y.: Unbiasing truncated backpropagation through time. arXiv preprint arXiv:1705.08209 (2017)

  32. Wu, S., Tang, Y., Zhu, Y., Wang, L., Xie, X., Tan, T.: Session-based recommendation with graph neural networks. In: AAAI (2019)

    Google Scholar 

  33. Yu, F., Zhu, Y., Liu, Q., Wu, S., Wang, L., Tan, T.: TAGNN: target attentive graph neural networks for session-based recommendation. association for computing machinery (2020)

    Google Scholar 

  34. Yuan, F., Karatzoglou, A., Arapakis, I., Jose, J.M., He, X.: A simple but hard-to-beat baseline for session-based recommendations (2018), http://arxiv.org/abs/1808.05163

Download references

Acknowledgements

Barbara Rychalska was supported by grant no 2018/31/N/ST6/02273 funded by National Science Centre, Poland.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Barbara Rychalska .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2021 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Dąbrowski, J. et al. (2021). An Efficient Manifold Density Estimator for All Recommendation Systems. In: Mantoro, T., Lee, M., Ayu, M.A., Wong, K.W., Hidayanto, A.N. (eds) Neural Information Processing. ICONIP 2021. Lecture Notes in Computer Science(), vol 13111. Springer, Cham. https://doi.org/10.1007/978-3-030-92273-3_27

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-92273-3_27

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-92272-6

  • Online ISBN: 978-3-030-92273-3

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics