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

Can One Embedding Fit All? A Multi-Interest Learning Paradigm Towards Improving User Interest Diversity Fairness (2402.13495v1)

Published 21 Feb 2024 in cs.IR

Abstract: Recommender systems (RSs) have gained widespread applications across various domains owing to the superior ability to capture users' interests. However, the complexity and nuanced nature of users' interests, which span a wide range of diversity, pose a significant challenge in delivering fair recommendations. In practice, user preferences vary significantly; some users show a clear preference toward certain item categories, while others have a broad interest in diverse ones. Even though it is expected that all users should receive high-quality recommendations, the effectiveness of RSs in catering to this disparate interest diversity remains under-explored. In this work, we investigate whether users with varied levels of interest diversity are treated fairly. Our empirical experiments reveal an inherent disparity: users with broader interests often receive lower-quality recommendations. To mitigate this, we propose a multi-interest framework that uses multiple (virtual) interest embeddings rather than single ones to represent users. Specifically, the framework consists of stacked multi-interest representation layers, which include an interest embedding generator that derives virtual interests from shared parameters, and a center embedding aggregator that facilitates multi-hop aggregation. Experiments demonstrate the effectiveness of the framework in achieving better trade-off between fairness and utility across various datasets and backbones.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (44)
  1. Charu C Aggarwal. 2016. Evaluating recommender systems. Recommender Systems: The Textbook (2016), 225–254.
  2. Controllable multi-interest framework for recommendation. In Proceedings of KDD. 2942–2951.
  3. Structured graph convolutional networks with stochastic masks for recommender systems. In Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval.
  4. Graph neural transport networks with non-local attentions for recommender systems. In Proceedings of the ACM Web Conference 2022.
  5. PersonaSAGE: A Multi-Persona Graph Neural Network. arXiv preprint arXiv:2212.13709 (2022).
  6. Large Language Models for User Interest Journeys. arXiv preprint arXiv:2305.15498 (2023).
  7. A flexible framework for evaluating user and item fairness in recommender systems. User Modeling and User-Adapted Interaction (2021), 1–55.
  8. Alessandro Epasto and Bryan Perozzi. 2019. Is a single embedding enough? learning node representations that capture multiple social contexts. In The world wide web conference. 394–404.
  9. Graph neural networks for social recommendation. In The world wide web conference. 417–426.
  10. A fairness-aware hybrid recommender system. arXiv preprint arXiv:1809.09030 (2018).
  11. Fairness-aware explainable recommendation over knowledge graphs. In Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. 69–78.
  12. On the problem of underranking in group-fair ranking. In International Conference on Machine Learning. PMLR, 3777–3787.
  13. Fairness without demographics in repeated loss minimization. In International Conference on Machine Learning. PMLR, 1929–1938.
  14. Lightgcn: Simplifying and powering graph convolution network for recommendation. In Proceedings of the 43rd International ACM SIGIR conference on research and development in Information Retrieval. 639–648.
  15. LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning. arXiv preprint arXiv:2401.01325 (2024).
  16. Fairness without demographics through adversarially reweighted learning. Advances in neural information processing systems 33 (2020), 728–740.
  17. Multi-interest network with dynamic routing for recommendation at Tmall. In Proceedings of the 28th ACM international conference on information and knowledge management. 2615–2623.
  18. User-oriented fairness in recommendation. In Proceedings of the Web Conference 2021. 624–632.
  19. Fairness in recommendation: A survey. arXiv preprint arXiv:2205.13619 (2022).
  20. Personalized news recommendation based on click behavior. In Proceedings of the 15th international conference on Intelligent user interfaces. 31–40.
  21. James MacQueen et al. 1967. Some methods for classification and analysis of multivariate observations. In Proceedings of the fifth Berkeley symposium on mathematical statistics and probability, Vol. 1. Oakland, CA, USA, 281–297.
  22. Pinnersage: Multi-modal user embedding framework for recommendations at pinterest. In SIGKDD. 2311–2320.
  23. Unsupervised differentiable multi-aspect network embedding. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 1435–1445.
  24. The unfairness of active users and popularity bias in point-of-interest recommendation. In International Workshop on Algorithmic Bias in Search and Recommendation. Springer, 56–68.
  25. BPR: Bayesian personalized ranking from implicit feedback. arXiv preprint arXiv:1205.2618 (2012).
  26. Every Preference Changes Differently: Neural Multi-Interest Preference Model with Temporal Dynamics for Recommendation. arXiv (2022).
  27. Edward H Simpson. 1949. Measurement of diversity. nature 163, 4148 (1949), 688–688.
  28. Robert L Thorndike. 1953. Who belongs in the family? Psychometrika 18, 4 (1953), 267–276.
  29. Towards representation alignment and uniformity in collaborative filtering. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 1816–1825.
  30. Tongzhou Wang and Phillip Isola. 2020. Understanding contrastive representation learning through alignment and uniformity on the hypersphere. In International Conference on Machine Learning. PMLR, 9929–9939.
  31. A survey on the fairness of recommender systems. ACM Transactions on Information Systems 41, 3 (2023), 1–43.
  32. Improving fairness in graph neural networks via mitigating sensitive attribute leakage. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining.
  33. Collaboration-Aware Graph Convolutional Network for Recommender Systems. In Proceedings of the ACM Web Conference 2023. 91–101.
  34. Joe H Ward Jr. 1963. Hierarchical grouping to optimize an objective function. Journal of the American statistical association 58, 301 (1963), 236–244.
  35. Are Big Recommendation Models Fair to Cold Users? arXiv preprint arXiv:2202.13607 (2022).
  36. Fairness-aware news recommendation with decomposed adversarial learning. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 35. 4462–4469.
  37. From Trainable Negative Depth to Edge Heterophily in Graphs. In Thirty-seventh Conference on Neural Information Processing Systems.
  38. Reconciling Competing Sampling Strategies of Network Embedding. In Thirty-seventh Conference on Neural Information Processing Systems.
  39. Bright: A bridging algorithm for network alignment. In Proceedings of the Web Conference 2021.
  40. Dissecting cross-layer dependency inference on multi-layered inter-dependent networks. In Proceedings of the 31st ACM International Conference on Information & Knowledge Management.
  41. Re4: Learning to Re-contrast, Re-attend, Re-construct for Multi-interest Recommendation. In WebConf. 2216–2226.
  42. Fairness and Diversity in Recommender Systems: A Survey. arXiv preprint arXiv:2307.04644 (2023).
  43. Leveraging Opposite Gender Interaction Ratio as a Path towards Fairness in Online Dating Recommendations Based on User Sexual Orientation. In Proceedings of the AAAI Conference on Artificial Intelligence.
  44. Fairness-aware tensor-based recommendation. In Proceedings of the 27th ACM international conference on information and knowledge management. 1153–1162.
Citations (4)
View on Semantic Scholar

Summary

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

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