Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
119 tokens/sec
GPT-4o
56 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

A Data-Centric Multi-Objective Learning Framework for Responsible Recommendation Systems (2310.13260v1)

Published 20 Oct 2023 in cs.IR

Abstract: Recommendation systems effectively guide users in locating their desired information within extensive content repositories. Generally, a recommendation model is optimized to enhance accuracy metrics from a user utility standpoint, such as click-through rate or matching relevance. However, a responsible industrial recommendation system must address not only user utility (responsibility to users) but also other objectives, including increasing platform revenue (responsibility to platforms), ensuring fairness (responsibility to content creators), and maintaining unbiasedness (responsibility to long-term healthy development). Multi-objective learning is a potent approach for achieving responsible recommendation systems. Nevertheless, current methods encounter two challenges: difficulty in scaling to heterogeneous objectives within a unified framework, and inadequate controllability over objective priority during optimization, leading to uncontrollable solutions. In this paper, we present a data-centric optimization framework, MoRec, which unifies the learning of diverse objectives. MoRec is a tri-level framework: the outer level manages the balance between different objectives, utilizing a proportional-integral-derivative (PID)-based controller to ensure a preset regularization on the primary objective. The middle level transforms objective-aware optimization into data sampling weights using sign gradients. The inner level employs a standard optimizer to update model parameters with the sampled data. Consequently, MoRec can flexibly support various objectives while maintaining the original model intact. Comprehensive experiments on two public datasets and one industrial dataset showcase the effectiveness, controllability, flexibility, and Pareto efficiency of MoRec, making it highly suitable for real-world implementation.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (50)
  1. Karl Johan Åström and Tore Hägglund. 2006a. Advanced PID control. ISA-The Instrumentation, Systems and Automation Society.
  2. Karl J Åström and Tore Hägglund. 2006b. PID control. IEEE Control Systems Magazine 1066 (2006).
  3. Putting fairness principles into practice: Challenges, metrics, and improvements. In Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society. 453–459.
  4. A hybrid recommendation system with many-objective evolutionary algorithm. Expert Systems with Applications 159 (2020), 113648.
  5. Vira Chankong and Yacov Y Haimes. 2008. Multiobjective decision making: theory and methodology. Courier Dover Publications.
  6. Wide & deep learning for recommender systems. In Proceedings of the 1st workshop on deep learning for recommender systems. 7–10.
  7. A novel multi-objective evolutionary algorithm for recommendation systems. J. Parallel and Distrib. Comput. 103 (2017), 53–63.
  8. Indraneel Das and John E Dennis Jr. 1996. A closer look at drawbacks of minimizing weighted sums of objectives for Pareto set generation in multicriteria optimization problems. Technical Report.
  9. A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE transactions on evolutionary computation 6, 2 (2002), 182–197.
  10. Jean-Antoine Désidéri. 2012. Multiple-gradient descent algorithm (MGDA) for multiobjective optimization. Comptes Rendus Mathematique 350, 5-6 (2012), 313–318.
  11. Francis Ysidro Edgeworth. 1881. Mathematical psychics: An essay on the application of mathematics to the moral sciences. Vol. 10. CK Paul.
  12. Carlos M Fonseca and Peter J Fleming. 1993. Multiobjective genetic algorithms. In IEE colloquium on genetic algorithms for control systems engineering. Iet, 6–1.
  13. Toward Pareto efficient fairness-utility trade-off in recommendation through reinforcement learning. In Proceedings of the fifteenth ACM international conference on web search and data mining. 316–324.
  14. DeepFM: a factorization-machine based neural network for CTR prediction. arXiv preprint arXiv:1703.04247 (2017).
  15. Xiangnan He and Tat-Seng Chua. 2017. Neural factorization machines for sparse predictive analytics. In Proceedings of the 40th International ACM SIGIR conference on Research and Development in Information Retrieval. 355–364.
  16. Neural collaborative filtering. In Proceedings of the 26th international conference on world wide web. 173–182.
  17. Session-based recommendations with recurrent neural networks. arXiv preprint arXiv:1511.06939 (2015).
  18. Dietmar Jannach. 2022. Multi-objective recommendation: Overview and challenges. In Proceedings of the 2nd Workshop on Multi-Objective Recommender Systems co-located with 16th ACM Conference on Recommender Systems (RecSys 2022), Vol. 3268.
  19. Christopher C Johnson. 2014. Logistic matrix factorization for implicit feedback data. Advances in Neural Information Processing Systems 27, 78 (2014), 1–9.
  20. Wang-Cheng Kang and Julian McAuley. 2018. Self-attentive sequential recommendation. In 2018 IEEE international conference on data mining (ICDM). IEEE, 197–206.
  21. xdeepfm: Combining explicit and implicit feature interactions for recommender systems. In Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery & data mining. 1754–1763.
  22. A pareto-efficient algorithm for multiple objective optimization in e-commerce recommendation. In Proceedings of the 13th ACM Conference on recommender systems. 20–28.
  23. Pareto multi-task learning. Advances in neural information processing systems 32 (2019).
  24. Joint Optimization of Profit and Relevance for Recommendation Systems in E-commerce.. In RMSE@ RecSys.
  25. Efficient continuous pareto exploration in multi-task learning. In International Conference on Machine Learning. PMLR, 6522–6531.
  26. Debabrata Mahapatra and Vaibhav Rajan. 2020. Multi-task learning with user preferences: Gradient descent with controlled ascent in pareto optimization. In International Conference on Machine Learning. PMLR, 6597–6607.
  27. Andriy Mnih and Russ R Salakhutdinov. 2007. Probabilistic matrix factorization. Advances in neural information processing systems 20 (2007).
  28. Using multi-objective optimization to solve the long tail problem in recommender system. In Advances in Knowledge Discovery and Data Mining: 23rd Pacific-Asia Conference, PAKDD 2019, Macau, China, April 14-17, 2019, Proceedings, Part III 23. Springer, 302–313.
  29. Steffen Rendle and Christoph Freudenthaler. 2014. Improving pairwise learning for item recommendation from implicit feedback. In Proceedings of the 7th ACM international conference on Web search and data mining. 273–282.
  30. BPR: Bayesian personalized ranking from implicit feedback. arXiv preprint arXiv:1205.2618 (2012).
  31. Pareto-efficient hybridization for multi-objective recommender systems. In Proceedings of the sixth ACM conference on Recommender systems. 19–26.
  32. Multiobjective pareto-efficient approaches for recommender systems. ACM Transactions on Intelligent Systems and Technology (TIST) 5, 4 (2014), 1–20.
  33. FairBatch: Batch Selection for Model Fairness. In ICLR. OpenReview.net.
  34. J David Schaffer. 2014. Multiple objective optimization with vector evaluated genetic algorithms. In Proceedings of the first international conference on genetic algorithms and their applications. Psychology Press, 93–100.
  35. Ozan Sener and Vladlen Koltun. 2018. Multi-task learning as multi-objective optimization. Advances in neural information processing systems 31 (2018).
  36. ControlVAE: Controllable Variational Autoencoder, Vol. 119. PMLR, 8655–8664. http://proceedings.mlr.press/v119/shao20b.html
  37. Autoint: Automatic feature interaction learning via self-attentive neural networks. In Proceedings of the 28th ACM International Conference on Information and Knowledge Management. 1161–1170.
  38. Jiaxi Tang and Ke Wang. 2018. Personalized top-n sequential recommendation via convolutional sequence embedding. In Proceedings of the eleventh ACM international conference on web search and data mining. 565–573.
  39. Deep & cross network for ad click predictions. In Proceedings of the ADKDD’17. 1–7.
  40. Multi-objective optimization for long tail recommendation. Knowledge-Based Systems 104 (2016), 145–155.
  41. Recommendation algorithms for optimizing hit rate, user satisfaction and website revenue. In Twenty-Fourth International Joint Conference on Artificial Intelligence.
  42. Graph neural networks in recommender systems: a survey. Comput. Surveys 55, 5 (2022), 1–37.
  43. Fairness-aware group recommendation with pareto-efficiency. In Proceedings of the eleventh ACM conference on recommender systems. 107–115.
  44. Personalized approximate pareto-efficient recommendation. In Proceedings of the Web Conference 2021. 3839–3849.
  45. Do Current Multi-Task Optimization Methods in Deep Learning Even Help? Advances in Neural Information Processing Systems 35 (2022), 13597–13609.
  46. Graph convolutional neural networks for web-scale recommender systems. In Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery & data mining. 974–983.
  47. Po-Lung Yu. 1973. A class of solutions for group decision problems. Management science 19, 8 (1973), 936–946.
  48. Yong Zheng and David Xuejun Wang. 2022. A survey of recommender systems with multi-objective optimization. Neurocomputing 474 (2022), 141–153.
  49. Deep interest network for click-through rate prediction. In Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery & data mining. 1059–1068.
  50. Personalized recommendation based on evolutionary multi-objective optimization [research frontier]. IEEE Computational Intelligence Magazine 10, 1 (2015), 52–62.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (5)
  1. Xu Huang (56 papers)
  2. Jianxun Lian (39 papers)
  3. Hao Wang (1120 papers)
  4. Defu Lian (142 papers)
  5. Xing Xie (220 papers)

Summary

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

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