Papers
Topics
Authors
Recent
Search
2000 character limit reached

Towards a Theoretical Understanding of Two-Stage Recommender Systems

Published 23 Feb 2024 in cs.IR and cs.AI | (2403.00802v1)

Abstract: Production-grade recommender systems rely heavily on a large-scale corpus used by online media services, including Netflix, Pinterest, and Amazon. These systems enrich recommendations by learning users' and items' embeddings projected in a low-dimensional space with two-stage models (two deep neural networks), which facilitate their embedding constructs to predict users' feedback associated with items. Despite its popularity for recommendations, its theoretical behaviors remain comprehensively unexplored. We study the asymptotic behaviors of the two-stage recommender that entail a strong convergence to the optimal recommender system. We establish certain theoretical properties and statistical assurance of the two-stage recommender. In addition to asymptotic behaviors, we demonstrate that the two-stage recommender system attains faster convergence by relying on the intrinsic dimensions of the input features. Finally, we show numerically that the two-stage recommender enables encapsulating the impacts of items' and users' attributes on ratings, resulting in better performance compared to existing methods conducted using synthetic and real-world data experiments.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (54)
  1. Tensorflow: A system for large-scale machine learning. In Proceedings of the 12th USENIX Conference on Operating Systems Design and Implementation, OSDI’16, pp.  265–283, USA, 2016. USENIX Association. ISBN 9781931971331.
  2. A group-specific recommender system. Journal of the American Statistical Association, 112(519):1344–1353, 2017.
  3. Casmos: A framework for learning candidate selection models over structured queries and documents. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp.  441–450, 2016.
  4. Tasteweights: a visual interactive hybrid recommender system. In Proceedings of the sixth ACM conference on Recommender systems, pp.  35–42, 2012.
  5. Burke, R. Hybrid recommender systems: Survey and experiments. User modeling and user-adapted interaction, 12:331–370, 2002.
  6. Controllable multi-interest framework for recommendation. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp.  2942–2951, 2020.
  7. Maximum block improvement and polynomial optimization. SIAM Journal on Optimization, 22(1):87–107, 2012.
  8. Top-k off-policy correction for a reinforce recommender system. In Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining, pp.  456–464, 2019a.
  9. Efficient approximation of deep relu networks for functions on low dimensional manifolds. Advances in neural information processing systems, 32, 2019b.
  10. Pixie: A system for recommending 3+ billion items to 200+ million users in real-time. In Proceedings of the 2018 world wide web conference, pp.  1775–1784, 2018.
  11. When recommenders fail: predicting recommender failure for algorithm selection and combination. In Proceedings of the sixth ACM conference on Recommender systems, pp.  233–236, 2012.
  12. Falconer, K. Fractal geometry: mathematical foundations and applications. John Wiley & Sons, 2004.
  13. Real-time news recommender system. In Machine Learning and Knowledge Discovery in Databases: European Conference, ECML PKDD 2010, Barcelona, Spain, September 20-24, 2010, Proceedings, Part III 21, pp.  583–586. Springer, 2010.
  14. Graph enhanced representation learning for news recommendation. In Proceedings of The Web Conference 2020, pp.  2863–2869, 2020.
  15. A hybrid approach using collaborative filtering and content based filtering for recommender system. In Journal of Physics: Conference Series, volume 1000, pp.  012101. IOP Publishing, 2018.
  16. A unified approach to building hybrid recommender systems. In Proceedings of the third ACM conference on Recommender systems, pp.  117–124, 2009.
  17. Hofmann, T. Latent semantic models for collaborative filtering. ACM Transactions on Information Systems (TOIS), 22(1):89–115, 2004.
  18. Latent class models for collaborative filtering. In IJCAI, volume 99, 1999.
  19. Hug, N. Surprise: A python library for recommender systems. Journal of Open Source Software, 5(52):2174, 2020.
  20. Candidate generation with binary codes for large-scale top-n recommendation. In Proceedings of the 28th ACM international conference on information and knowledge management, pp.  1523–1532, 2019.
  21. Matrix factorization techniques for recommender systems. Computer, 42(8):30–37, 2009.
  22. Hyper: A flexible and extensible probabilistic framework for hybrid recommender systems. In Proceedings of the 9th ACM Conference on Recommender Systems, pp.  99–106, 2015.
  23. Lang, K. Newsweeder: Learning to filter netnews. In Machine learning proceedings 1995, pp.  331–339. Elsevier, 1995.
  24. Context-aware advertisement recommendation for high-speed social news feeding. In 2016 IEEE 32nd International Conference on Data Engineering (ICDE), pp.  505–516. IEEE, 2016.
  25. Smooth bandit optimization: generalization to holder space. In International Conference on Artificial Intelligence and Statistics, pp.  2206–2214. PMLR, 2021.
  26. Deep unified representation for heterogeneous recommendation. In Proceedings of the ACM Web Conference 2022, pp.  2141–2152, 2022.
  27. Metaselector: Meta-learning for recommendation with user-level adaptive model selection. In Proceedings of The Web Conference 2020, pp.  2507–2513, 2020.
  28. Matrix completion with covariate information. Journal of the American Statistical Association, 114(525):198–210, 2019.
  29. Spectral regularization algorithms for learning large incomplete matrices. The Journal of Machine Learning Research, 11:2287–2322, 2010.
  30. Ontological user profiling in recommender systems. ACM Transactions on Information Systems (TOIS), 22(1):54–88, 2004.
  31. Movielens unplugged: experiences with an occasionally connected recommender system. In Proceedings of the 8th international conference on Intelligent user interfaces, pp.  263–266, 2003.
  32. Adaptive approximation and generalization of deep neural network with intrinsic dimensionality. The Journal of Machine Learning Research, 21(1):7018–7055, 2020.
  33. Context-aware svm for context-dependent information recommendation. In 7th International Conference on Mobile Data Management (MDM’06), pp.  109–109. IEEE, 2006.
  34. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems, 32, 2019.
  35. Content-based recommendation systems. The adaptive web: methods and strategies of web personalization, pp.  325–341, 2007.
  36. Online shopping recommender system using hybrid method. In 2013 International Conference of Information and Communication Technology (ICoICT), pp.  166–169. IEEE, 2013.
  37. Restricted boltzmann machines for collaborative filtering. In Proceedings of the 24th international conference on Machine learning, pp.  791–798, 2007.
  38. Collaborative filtering recommender systems. The adaptive web: methods and strategies of web personalization, pp.  291–324, 2007.
  39. Convergence rate of sieve estimates. The Annals of Statistics, pp.  580–615, 1994.
  40. Adaptive knn based recommender system through mining of user preferences. Wireless Personal Communications, 97:2229–2247, 2017.
  41. Multimodal review generation for recommender systems. In The World Wide Web Conference, pp.  1864–1874, 2019.
  42. Twardowski, B. Modelling contextual information in session-aware recommender systems with neural networks. In Proceedings of the 10th ACM Conference on Recommender Systems, pp.  273–276, 2016.
  43. Deep content-based music recommendation. Advances in neural information processing systems, 26, 2013.
  44. Effects of relevant contextual features in the performance of a restaurant recommender system. ACM RecSys, 11(592):56, 2011.
  45. Dynamic causal collaborative filtering. In Proceedings of the 31st ACM International Conference on Information & Knowledge Management, pp.  2301–2310, 2022.
  46. Deconfounded causal collaborative filtering. ACM Transactions on Recommender Systems, 1(4):1–25, 2023.
  47. Mixed negative sampling for learning two-tower neural networks in recommendations. In Companion Proceedings of the Web Conference 2020, pp.  441–447, 2020.
  48. Sampling-bias-corrected neural modeling for large corpus item recommendations. In Proceedings of the 13th ACM Conference on Recommender Systems, pp.  269–277, 2019.
  49. A visual dialog augmented interactive recommender system. In Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining, pp.  157–165, 2019.
  50. Robust collaborative filtering to popularity distribution shift. ACM Transactions on Information Systems, 2023.
  51. Zhang, T. Covering number bounds of certain regularized linear function classes. Journal of Machine Learning Research, 2(Mar):527–550, 2002.
  52. Recommending what video to watch next: a multitask ranking system. In Proceedings of the 13th ACM Conference on Recommender Systems, pp.  43–51, 2019.
  53. Zhou, D.-X. The covering number in learning theory. Journal of Complexity, 18(3):739–767, 2002.
  54. Personalized prediction and sparsity pursuit in latent factor models. Journal of the American Statistical Association, 111(513):241–252, 2016.

Summary

No one has generated a summary of this paper yet.

Sign Up to Summarize

Paper to Video (Beta)

No one has generated a video about this paper yet.

Sign Up to Generate All Videos Subscribe on YouTube

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Generate Now

Authors (1)

  1. Amit Kumar Jaiswal 

Collections

Sign up for free to add this paper to one or more collections.

Sign Up