Countering Mainstream Bias via End-to-End Adaptive Local Learning: Conclusion and References

Table of Links

Abstract and 1 Introduction

2 Preliminaries

3 End-to-End Adaptive Local Learning

3.1 Loss-Driven Mixture-of-Experts

3.2 Synchronized Learning via Adaptive Weight

4 Debiasing Experiments and 4.1 Experimental Setup

4.2 Debiasing Performance

4.3 Ablation Study

4.4 Effect of the Adaptive Weight Module and 4.5 Hyper-parameter Study

5 Related Work

6 Conclusion, Acknowledgements, and References

6 Conclusion

In this study, we aim to address the mainstream bias in recommender systems that niche users who possess special and minority interests receive overly low utility from recommendation models. We identify two root causes of this bias: the discrepancy modeling problem and the unsynchronized learning problem. Toward debiasing, we devise an end-to-end adaptive local learning framework: we first propose a loss-driven Mixture-of-Experts module to counteract the discrepancy modeling problem, and then we develop an adaptive weight module to fight against the unsynchronized learning problem. Extensive experiments show the outstanding performance of our proposed method on both niche and mainstream users and overall performance compared to SOTA alternatives.

Acknowledgements. This research was funded in part by 4-VA, a collaborative partnership for advancing the Commonwealth of Virginia.

References

1. Yelp dataset (2021), https://www.yelp.com/dataset

   
   

2. Abdollahpouri, H., Burke, R., Mobasher, B.: Controlling popularity bias in learning-to-rank recommendation. In: Proceedings of the eleventh ACM conference on recommender systems. pp. 42–46 (2017)

   
   

3. Abdollahpouri, H., Burke, R., Mobasher, B.: Managing popularity bias in recommender systems with personalized re-ranking. In: The thirty second international flairs conference (2019)

   
   

4. Alabdulrahman, R., Viktor, H.: Catering for unique tastes: Targeting grey-sheep users recommender systems through one-class machine learning. Expert Systems with Applications 166, 114061 (2021)

   
   

5. Ben-Porat, O., Torkan, R.: Learning with exposure constraints in recommendation systems. In: Proceedings of the ACM Web Conference 2023. pp. 3456–3466 (2023)

   
   

6. Beutel, A., Chen, J., Doshi, T., Qian, H., Wei, L., Wu, Y., Heldt, L., Zhao, Z., Hong, L., Chi, E.H., et al.: Fairness in recommendation ranking through pairwise comparisons. In: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. pp. 2212–2220 (2019)

   
   

7. Cai, W., Feng, F., Wang, Q., Yang, T., Liu, Z., Xu, C.: A causal view for item-level effect of recommendation on user preference. In: Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining. pp. 240–248 (2023)

   
   

8. Chai, J., Wang, X.: Fairness with adaptive weights. In: International Conference on Machine Learning. pp. 2853–2866. PMLR (2022)

   
   

9. Chen, J., Wu, J., Chen, J., Xin, X., Li, Y., He, X.: How graph convolutions amplify popularity bias for recommendation? arXiv preprint arXiv:2305.14886 (2023)

   
   

10. Chen, L., Wu, L., Zhang, K., Hong, R., Lian, D., Zhang, Z., Zhou, J., Wang, M.: Improving recommendation fairness via data augmentation. arXiv preprint arXiv:2302.06333 (2023)

    
    

11. Chen, X., Fan, W., Chen, J., Liu, H., Liu, Z., Zhang, Z., Li, Q.: Fairly adaptive negative sampling for recommendations. arXiv preprint arXiv:2302.08266 (2023)

    
    

12. Choi, M., Jeong, Y., Lee, J., Lee, J.: Local collaborative autoencoders. In: Proceedings of the 14th ACM International Conference on Web Search and Data Mining. pp. 734–742 (2021)

    
    

13. Christakopoulou, E., Karypis, G.: Local latent space models for top-n recommendation. In: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. pp. 1235–1243 (2018)

    
    

14. Eigen, D., Ranzato, M., Sutskever, I.: Learning factored representations in a deep mixture of experts. arXiv preprint arXiv:1312.4314 (2013)

    
    

15. Ekstrand, M.D., Tian, M., Azpiazu, I.M., Ekstrand, J.D., Anuyah, O., McNeill, D., Pera, M.S.: All the cool kids, how do they fit in?: Popularity and demographic biases in recommender evaluation and effectiveness. In: Conference on fairness, accountability and transparency. pp. 172–186. PMLR (2018)

    
    

16. Fu, Z., Xian, Y., Gao, R., Zhao, J., Huang, Q., Ge, Y., Xu, S., Geng, S., Shah, C., Zhang, Y., et al.: Fairness-aware explainable recommendation over knowledge graphs. In: Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. pp. 69–78 (2020)

    
    

17. Geyik, S.C., Ambler, S., Kenthapadi, K.: Fairness-aware ranking in search & recommendation systems with application to linkedin talent search. In: Proceedings of the 25th acm sigkdd international conference on knowledge discovery & data mining. pp. 2221–2231 (2019)

    
    

18. Gras, B., Brun, A., Boyer, A.: Can matrix factorization improve the accuracy of recommendations provided to grey sheep users? In: 13th international conference on Web Information Systems and Technologies (WEBIST). pp. 88–96 (2017)

    
    

19. Harper, F.M., Konstan, J.A.: The movielens datasets: History and context. Acm transactions on interactive intelligent systems (tiis) 5(4), 1–19 (2015)

    
    

20. Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)

    
    

21. Lee, J.w., Park, S., Lee, J.: Dual unbiased recommender learning for implicit feedback. In: Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval. pp. 1647–1651 (2021)

    
    

22. Lee, J., Kim, S., Lebanon, G., Singer, Y.: Local low-rank matrix approximation. In: International conference on machine learning. pp. 82–90. PMLR (2013)

    
    

23. Lee, J., Kim, S., Lebanon, G., Singer, Y., Bengio, S.: Llorma: Local low-rank matrix approximation (2016)

    
    

24. Li, R.Z., Urbano, J., Hanjalic, A.: Leave no user behind: Towards improving the utility of recommender systems for non-mainstream users. In: Proceedings of the 14th ACM International Conference on Web Search and Data Mining. pp. 103–111 (2021)

    
    

25. Li, Y., Chen, H., Fu, Z., Ge, Y., Zhang, Y.: User-oriented fairness in recommendation. In: Proceedings of the Web Conference 2021. pp. 624 632 (2021)

    
    

26. Liang, D., Krishnan, R.G., Hoffman, M.D., Jebara, T.: Variational autoencoders for collaborative filtering. In: Proceedings of the 2018 world wide web conference. pp. 689–698 (2018)

    
    

27. Liu, W., Burke, R.: Personalizing fairness-aware re-ranking. arXiv preprint arXiv:1809.02921 (2018)

    
    

28. Ni, J., Li, J., McAuley, J.: Justifying recommendations using distantly-labeled reviews and fine-grained aspects. In: Proceedings of the 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing (EMNLP-IJCNLP). pp. 188–197 (2019)

    
    

29. Rawls, J.: Justice as fairness: A restatement. Harvard University Press (2001)

    
    

30. Saito, Y.: Unbiased pairwise learning from biased implicit feedback. In: Proceedings of the 2020 ACM SIGIR on International Conference on Theory of Information Retrieval. pp. 5–12 (2020)

    
    

31. Saito, Y., Yaginuma, S., Nishino, Y., Sakata, H., Nakata, K.: Unbiased recommender learning from missing-not-at-random implicit feedback. In: Proceedings of the 13th International Conference on Web Search and Data Mining. pp. 501–509 (2020)

    
    

32. Schedl, M., Bauer, C.: Online music listening culture of kids and adolescents: Listening analysis and music recommendation tailored to the young. arXiv preprint arXiv:1912.11564 (2019

33. 
    

34. Wang, Y., Ma, W., Zhang, M., Liu, Y., Ma, S.: A survey on the fairness of recommender systems. ACM Transactions on Information Systems 41(3), 1–43 (2023)

    
    

35. Wei, T., Feng, F., Chen, J., Shi, C., Wu, Z., Yi, J., He, X.: Model-agnostic counterfactual reasoning for eliminating popularity bias in recommender system. arXiv preprint arXiv:2010.15363 (2020)

    
    

36. Yao, S., Huang, B.: Beyond parity: Fairness objectives for collaborative filtering. arXiv preprint arXiv:1705.08804 (2017)

    
    

37. Ying, Y., Zhuang, F., Zhu, Y., Wang, D., Zheng, H.: Camus: Attribute-aware counterfactual augmentation for minority users in recommendation. In: Proceedings of the ACM Web Conference 2023. pp. 1396–1404 (2023)

    
    

38. Zhang, Y., Feng, F., He, X., Wei, T., Song, C., Ling, G., Zhang, Y.: Causal intervention for leveraging popularity bias in recommendation. arXiv preprint arXiv:2105.06067 (2021)

    
    

39. Zhang, Y., Cheng, D.Z., Yao, T., Yi, X., Hong, L., Chi, E.H.: A model of two tales: Dual transfer learning framework for improved long-tail item recommendation. In: Proceedings of the Web Conference 2021. pp. 2220–2231 (2021)

    
    

40. Zhu, Z., Caverlee, J.: Fighting mainstream bias in recommender systems via local fine tuning. In: Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining. pp. 1497–1506 (2022)