Papers
Topics
Authors
Recent
2000 character limit reached

Pareto-based Multi-Objective Recommender System with Forgetting Curve

Published 28 Dec 2023 in cs.IR | (2312.16868v2)

Abstract: Recommender systems with cascading architecture play an increasingly significant role in online recommendation platforms, where the approach to dealing with negative feedback is a vital issue. For instance, in short video platforms, users tend to quickly slip away from candidates that they feel aversive, and recommender systems are expected to receive these explicit negative feedbacks and make adjustments to avoid these recommendations. Considering recency effect in memories, we propose a forgetting model based on Ebbinghaus Forgetting Curve to cope with negative feedback. In addition, we introduce a Pareto optimization solver to guarantee a better trade-off between recency and model performance. In conclusion, we propose Pareto-based Multi-Objective Recommender System with forgetting curve (PMORS), which can be applied to any multi-objective recommendation and show sufficiently superiority when facing explicit negative feedback. We have conducted evaluations of PMORS and achieved favorable outcomes in short-video scenarios on both public dataset and industrial dataset. After being deployed on an online short video platform named WeChat Channels in May, 2023, PMORS has not only demonstrated promising results for both consistency and recency but also achieved an improvement of up to +1.45% GMV.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (75)
  1. On Hyperparameter Optimization of Machine Learning Methods Using a Bayesian Optimization Algorithm to Predict Work Travel Mode Choice. IEEE Access 11 (2023), 19762–19774.
  2. Daniel M. Belete and Manjaiah D. Huchaiah. 2022. Grid Search in Hyperparameter Optimization of Machine Learning Models for Prediction of HIV/AIDS Test Results. International Journal of Computers and Applications (IJCA) 44, 9 (2022), 875–886.
  3. Hyperparameter Optimization: Foundations, Algorithms, Best Practices, and Open Challenges. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery (WIREs) 13, 2 (2023), e1484.
  4. Learning to Rank Using Gradient Descent. In International Conference on Machine Learning(ICML). 89–96.
  5. Distributional Learning in Multi-Objective Optimization of Recommender Systems. Journal of Ambient Intelligence and Humanized Computing (JAIHC) 14, 8 (2023), 10849–10865.
  6. Revisiting Negative Sampling vs. Non-sampling in Implicit Recommendation. ACM Transactions on Information Systems(TOIS) 41, 1 (2023), 1–25.
  7. A Fuzzy Matrix Factor Recommendation Method with Forgetting Function and User Features. Applied Soft Computing (ASC) 100 (2021), 106910.
  8. Modeling the Interest-Forgetting Curve for Music Recommendation. In ACM International Conference on Multimedia (ICM). 921–924.
  9. Wide & Deep Learning for Recommender Systems. In Workshop on Deep Learning for Recommender Systems(DLRS). 7–10.
  10. Adaptive Factorization Network: Learning Adaptive-Order Feature Interactions. In the AAAI Conference on Artificial Intelligence(AAAI), Vol. 34. 3609–3616.
  11. CT4Rec: Simple yet Effective Consistency Training for Sequential Recommendation. In ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) (Long Beach, CA, USA). 3901–3913.
  12. A Multi-Objective Artificial Bee Colony Approach for Profit-Aware Recommender Systems. Information Sciences (IS) 625 (2023), 476–488.
  13. Jean-Antoine Désidéri. 2012. Multiple-Gradient Descent Algorithm (MGDA) for Multiobjective Optimization. Comptes Rendus Mathematique (CRM) 350, 5-6 (2012), 313–318.
  14. Hermann Ebbinghaus. 1885. Memory: A Contribution to Experimental Psychology. Teachers College, Columbia University, New York. Trans. HA Ruger and CE Bussenius. Original work published (1885).
  15. Recency Aware Collaborative Filtering for Next Basket Recommendation. In ACM Conference on User Modeling, Adaptation and Personalization (UMAP). 80–87.
  16. Forgetting Curve Models: A Systematic Review Aimed at Consolidating the Main Models and Outlining Possibilities for Future Research in Production. Expert Systems (ES) (2023), e13405.
  17. Individualized Extreme Dominance (IndED): A New Preference-Based Method for Multi-Objective Recommender Systems. Information Sciences (IS) 572 (2021), 558–573.
  18. An Algorithm for Quadratic Programming. Naval Research Logistics Quarterly(NRL) 3, 1-2 (1956), 95–110.
  19. KuaiRec: A Fully-Observed Dataset and Insights for Evaluating Recommender Systems. In ACM International Conference on Information & Knowledge Management(CIKM). 540–550.
  20. DRCGR: Deep Reinforcement Learning Framework Incorporating CNN and GAN-Based for Interactive Recommendation. In IEEE International Conference on Data Mining (ICDM). IEEE, 1048–1053.
  21. Toward Pareto Efficient Fairness-Utility Trade-Off in Recommendation Through Reinforcement Learning. In ACM International Conference on Web Search and Data Mining (WSDM). 316–324.
  22. DeepFM: A Factorization-Machine Based Neural Network for CTR Prediction. International Joint Conference on Artificial Intelligence(IJCAI) (2017).
  23. A Categorization of Workplace Learning Goals for Multi-Stakeholder Recommender Systems: A Systematic Review. TechTrends 67, 1 (2023), 98–111.
  24. Charles F. Hofacker and Jamie Murphy. 2009. Consumer Web Page Search, Clicking Behavior and Reaction Time. Direct Marketing: An International Journal 3, 2 (2009), 88–96.
  25. Negative Can Be Positive: Signed Graph Neural Networks for Recommendation. Information Processing & Management (IP&M) 60, 4 (2023), 103403.
  26. Accuracy-Diversity Trade-Off in Recommender Systems via Graph Convolutions. Information Processing & Management (IP&M) 58, 2 (2021), 102459.
  27. Diederik P. Kingma and Jimmy Ba. 2014. Adam: A Method for Stochastic Optimization. International Conference on Learning Representations(ICLR) (2014).
  28. Harold W. Kuhn and Albert W. Tucker. 2013. Nonlinear Programming. In Traces and Emergence of Nonlinear Programming. Springer, 247–258.
  29. Modeling and Applying Implicit Dormant Features for Recommendation via Clustering and Deep Factorization. Sensors 22, 21 (2022), 8224.
  30. Multi-Objective Optimization-Based Recommendation for Massive Online Learning Resources. IEEE Sensors Journal(IEEE Sens. J.) 21, 22 (2021), 25274–25281.
  31. On the Relationship between Explanation and Recommendation: Learning to Rank Explanations for Improved Performance. ACM Transactions on Intelligent Systems and Technology (TIST) 14, 2 (2023), 1–24.
  32. A Pareto-Efficient Algorithm for Multiple Objective Optimization in E-Commerce Recommendation. In ACM Conference on Recommender Systems (RecSys). ACM, 20–28.
  33. SMAC3: A Versatile Bayesian Optimization Package for Hyperparameter Optimization. The Journal of Machine Learning Research (JMLR) 23, 1 (2022), 2475–2483.
  34. Self-Attention Negative Feedback Network for Real-Time Image Super-Resolution. Journal of King Saud University-Computer and Information Sciences(J KING SAUD UNIV-COM) 34, 8 (2022), 6179–6186.
  35. The Irace Package: Iterated Racing for Automatic Algorithm Configuration. Operations Research Perspectives(Oper. Res. Perspect.) 3 (2016), 43–58.
  36. Modeling Task Relationships in Multi-Task Learning with Multi-Gate Mixture-Of-Experts. In ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD). 1930–1939.
  37. Modeling Task Relationships in Multi-task Learning with Multi-gate Mixture-of-Experts. In ACM SIGKDD International Conference on Knowledge Discovery & Data Mining(KDD). 1930–1939.
  38. Efficient Continuous Pareto Exploration in Multi-Task Learning. In International Conference on Machine Learning, ICML. PMLR, 6522–6531.
  39. Entire Space Multi-Task Model: An Effective Approach for Estimating Post-Click Conversion Rate. In International ACM SIGIR Conference on Research & Development in Information Retrieval(SIGIR). 1137–1140.
  40. Primacy and Recency Effects on Clicking Behavior. Journal of Computer-Mediated Communication (JCMC) 11, 2 (2006), 522–535.
  41. Improve Performance of Association Rule-Based Collaborative Filtering Recommendation Systems Using Genetic Algorithm. International Journal of Information Technology and Computer Science (IGITCS) 11, 2 (2019), 48–55.
  42. Improvising Personalized Travel Recommendation System with Recency Effects. Big Data Mining and Analytics 4, 3 (2021), 139–154.
  43. Vincenzo Paparella. 2022. Pursuing Optimal Trade-Off Solutions in Multi-Objective Recommender Systems. In ACM Conference on Recommender Systems (RecSys). 727–729.
  44. Post-hoc Selection of Pareto-Optimal Solutions in Search and Recommendation. ACM International Conference on Information and Knowledge Management(CIKM) abs/2306.12165 (2023), 2013–2023.
  45. A Review of Pareto Pruning Methods for Multi-Objective Optimization. Computers & Industrial Engineering (CAIE) 167 (2022), 108022.
  46. Slate-Aware Ranking for Recommendation. ACM International Conference on Web Search and Data Mining (WSDM), 499–507.
  47. Multi-Objective Pareto-Efficient Approaches for Recommender Systems. ACM Transactions on Intelligent Systems and Technology (TIST) 5, 4 (2014), 1–20.
  48. Ozan Sener and Vladlen Koltun. 2018. Multi-Task Learning as Multi-Objective Optimization. Advances in Neural Information Processing Systems(NeurIPS) 31 (2018).
  49. Deep Neural Network-Based Multi-Stakeholder Recommendation System Exploiting Multi-Criteria Ratings for Preference Learning. Expert Systems with Applications (ESWA) 213 (2023), 119071.
  50. BERD+: A Generic Sequential Recommendation Framework by Eliminating Unreliable Data with Item-and Attribute-Level Signals. ACM Transactions on Information Systems (TOIS) (2023).
  51. Progressive Layered Extraction (PLE): A Novel Multi-Task Learning (MTL) Model for Personalized Recommendations. In ACM Conference on Recommender Systems (RecSys). 269–278.
  52. DriveBFR: Driver Behavior and Fuel-Efficiency-Based Recommendation System. IEEE Transactions on Computational Social Systems (TCSS) 9, 5 (2021), 1446–1455.
  53. Attribute-Aware Multi-Task Recommendation. The Journal of Supercomputing(J Supercomput) 77 (2021), 4419–4437.
  54. Wei Wang and Longbing Cao. 2021. Interactive Sequential Basket Recommendation by Learning Basket Couplings and Positive/Negative Feedback. ACM Transactions on Information Systems (TOIS) 39, 3 (2021), 1–26.
  55. Learning from Negative User Feedback and Measuring Responsiveness for Sequential Recommenders. In ACM Conference on Recommender Systems (RecSys). 1049–1053.
  56. Multi-Task Deep Recommender Systems: A Survey. CoRR abs/2302.03525 (2023).
  57. Neural News Recommendation with Negative Feedback. CCF Transactions on Pervasive Computing and Interaction (CCF TPCI) 2 (2020), 178–188.
  58. Hyperparameter Learning for Deep Learning-Based Recommender Systems. IEEE Transactions on Services Computing (TSC) (2023), 2699–2712.
  59. A Multi-Objective Optimization Framework for Multi-Stakeholder Fairness-Aware Recommendation. ACM Transactions on Information Systems (TOIS) 41, 2 (2022), 1–29.
  60. A Survey on Accuracy-Oriented Neural Recommendation: From Collaborative Filtering to Information-Rich Recommendation. IEEE Transactions on Knowledge and Data Engineering (TKDE) 35, 5 (2022), 4425–4445.
  61. Adapting Boosting for Information Retrieval Measures. Information Retrieval 13 (2010), 254–270.
  62. On-device Integrated Re-ranking with Heterogeneous Behavior Modeling. In ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD). 5225–5236.
  63. Personalized Approximate Pareto-Efficient Recommendation. In ACM Web Conference (WWW) (Ljubljana, Slovenia). 3839–3849.
  64. Qian Xu. 2013. Social Recommendation, Source Credibility, and Recency: Effects of News Cues in a Social Bookmarking Website. Journalism & Mass Communication Quarterly (JMCQ) 90, 4 (2013), 757–775.
  65. Enhancing the Accuracy of Group Recommendation Using Slope One. The Journal of Supercomputing(J Supercomput) 79, 1 (2023), 499–540.
  66. Improving Group Recommendation Using Deep Collaborative Filtering Approach. International Journal of Information Technology (IJOIT) 15, 3 (2023), 1489–1497.
  67. Building User Interest Model for TV Recommendation with Label-Based Memory Forgetting-Enhancement Model. Multimedia Tools and Applications (MTAP) 81, 18 (2022), 26307–26330.
  68. A Selective Ensemble Learning Based Two-Sided Cross-Domain Collaborative Filtering Algorithm. Information Processing & Management (IP&M)(Inf Process Manag) 58, 6 (2021), 102691.
  69. Multi-Objective Optimization with Recommender Systems: A Systematic Review. Information Systems 117 (2023), 102233.
  70. An Indexed Set Representation Based Multi-Objective Evolutionary Approach for Mining Diversified Top-K High Utility Patterns. Engineering Applications of Artificial Intelligence (EAAI) 77 (2019), 9–20.
  71. COPR: Consistency-Oriented Pre-Ranking for Online Advertising. ACM International Conference on Information and Knowledge Management(CIKM) abs/2306.03516 (2023), 4974–4980.
  72. Tourism Route Recommendation Based on A Multi-Objective Evolutionary Algorithm Using Two-Stage Decomposition and Pareto Layering. IEEE/CAA Journal of Automatica Sinica(JAS) 10, 2 (2023), 486–500.
  73. S3-rec: Self-supervised learning for sequential recommendation with mutual information maximization. In ACM International Conference on Information & Knowledge Management (CIKM). 1893–1902.
  74. Integrated Ranking for News Feed with Reinforcement Learning. In ACM Web Conference(WWW). 480–484.
  75. A Two-Stage Personalized Recommendation Based on Multi-Objective Teaching–Learning-Based Optimization with Decomposition. Neurocomputing 452 (2021), 716–727.
Citations (2)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now

Whiteboard

Paper to Video (Beta)

Open Problems

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

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now

Continue Learning

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

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now

Collections

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

User Circle Single Streamline Icon: https://streamlinehq.com Sign Up