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

Enhanced Bayesian Personalized Ranking for Robust Hard Negative Sampling in Recommender Systems (2403.19276v1)

Published 28 Mar 2024 in cs.IR

Abstract: In implicit collaborative filtering, hard negative mining techniques are developed to accelerate and enhance the recommendation model learning. However, the inadvertent selection of false negatives remains a major concern in hard negative sampling, as these false negatives can provide incorrect information and mislead the model learning. To date, only a small number of studies have been committed to solve the false negative problem, primarily focusing on designing sophisticated sampling algorithms to filter false negatives. In contrast, this paper shifts its focus to refining the loss function. We find that the original Bayesian Personalized Ranking (BPR), initially designed for uniform negative sampling, is inadequate in adapting to hard sampling scenarios. Hence, we introduce an enhanced Bayesian Personalized Ranking objective, named as Hard-BPR, which is specifically crafted for dynamic hard negative sampling to mitigate the influence of false negatives. This method is simple yet efficient for real-world deployment. Extensive experiments conducted on three real-world datasets demonstrate the effectiveness and robustness of our approach, along with the enhanced ability to distinguish false negatives.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (40)
  1. Jessa Bekker and Jesse Davis. 2020. Learning from positive and unlabeled data: A survey. Machine Learning 109 (2020), 719–760.
  2. Hard Negatives or False Negatives: Correcting Pooling Bias in Training Neural Ranking Models. In Proceedings of the 31st ACM International Conference on Information & Knowledge Management. 118–127.
  3. Revisiting negative sampling vs. non-sampling in implicit recommendation. ACM Transactions on Information Systems 41, 1 (2023), 1–25.
  4. Learning Recommenders for Implicit Feedback with Importance Resampling. In Proceedings of the ACM Web Conference 2022. 1997–2005.
  5. On sampling strategies for neural network-based collaborative filtering. In Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 767–776.
  6. Simplify and robustify negative sampling for implicit collaborative filtering. Advances in Neural Information Processing Systems 33 (2020), 1094–1105.
  7. Gintare Karolina Dziugaite and Daniel M. Roy. 2015. Neural Network Matrix Factorization. CoRR (2015).
  8. Batch-Mix Negative Sampling for Learning Recommendation Retrievers. In Proceedings of the 32nd ACM International Conference on Information and Knowledge Management. 494–503.
  9. An equivalence between loss functions and non-uniform sampling in experience replay. Advances in neural information processing systems 33 (2020), 14219–14230.
  10. Wei Gao and Zhi-Hua Zhou. 2012. On the consistency of AUC pairwise optimization. arXiv preprint arXiv:1208.0645 (2012).
  11. 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, SIGIR 2020, Virtual Event, China, July 25-30, 2020. 639–648.
  12. 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.
  13. Collaborative filtering for implicit feedback datasets. In 2008 Eighth IEEE international conference on data mining. Ieee, 263–272.
  14. MixGCF: An Improved Training Method for Graph Neural Network-based Recommender Systems. In KDD ’21: The 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Virtual Event, Singapore, August 14-18, 2021, Feida Zhu, Beng Chin Ooi, and Chunyan Miao (Eds.). ACM, 665–674. https://doi.org/10.1145/3447548.3467408
  15. Mixgcf: An improved training method for graph neural network-based recommender systems. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining. 665–674.
  16. Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014).
  17. Yehuda Koren. 2008a. Factorization meets the neighborhood: a multifaceted collaborative filtering model. In Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Las Vegas, Nevada, USA, August 24-27, 2008. 426–434.
  18. Yehuda Koren. 2008b. Factorization meets the neighborhood: a multifaceted collaborative filtering model. In Proceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining. 426–434.
  19. Matrix Factorization Techniques for Recommender Systems. Computer 42, 8 (2009), 30–37.
  20. Daniel Lee and H Sebastian Seung. 2000. Algorithms for non-negative matrix factorization. Advances in neural information processing systems 13 (2000).
  21. Collaborative filtering with ordinal scale-based implicit ratings for mobile music recommendations. Information Sciences 180, 11 (2010), 2142–2155.
  22. Personalized ranking with importance sampling. In Proceedings of The Web Conference 2020. 1093–1103.
  23. Variational autoencoders for collaborative filtering. In Proceedings of the 2018 world wide web conference. 689–698.
  24. Andriy Mnih and Russ R Salakhutdinov. 2007. Probabilistic matrix factorization. Advances in neural information processing systems 20 (2007).
  25. Maryam Khanian Najafabadi and Mohd Naz’ri Mahrin. 2016. A systematic literature review on the state of research and practice of collaborative filtering technique and implicit feedback. Artificial intelligence review 45, 2 (2016), 167–201.
  26. One-class collaborative filtering. In 2008 Eighth IEEE international conference on data mining. IEEE, 502–511.
  27. Dae Hoon Park and Yi Chang. 2019. Adversarial sampling and training for semi-supervised information retrieval. In The World Wide Web Conference. 1443–1453.
  28. 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.
  29. BPR: Bayesian personalized ranking from implicit feedback. arXiv preprint arXiv:1205.2618 (2012).
  30. Ruslan Salakhutdinov and Andriy Mnih. 2007. Probabilistic Matrix Factorization. In Advances in Neural Information Processing Systems 20, Proceedings of the Twenty-First Annual Conference on Neural Information Processing Systems, Vancouver, British Columbia, Canada, December 3-6, 2007. 1257–1264.
  31. Soft BPR Loss for Dynamic Hard Negative Sampling in Recommender Systems. arXiv preprint arXiv:2211.13912 (2022).
  32. On the Theories Behind Hard Negative Sampling for Recommendation. In Proceedings of the ACM Web Conference 2023. 812–822.
  33. Graph Convolutional Matrix Completion. CoRR abs/1706.02263 (2017).
  34. Irgan: A minimax game for unifying generative and discriminative information retrieval models. In Proceedings of the 40th International ACM SIGIR conference on Research and Development in Information Retrieval. 515–524.
  35. KGAT: Knowledge Graph Attention Network for Recommendation. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, KDD 2019, Anchorage, AK, USA, August 4-8, 2019. 950–958.
  36. Neural Graph Collaborative Filtering. In Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2019, Paris, France, July 21-25, 2019. 165–174.
  37. Dimension Independent Mixup for Hard Negative Sample in Collaborative Filtering. In Proceedings of the 32nd ACM International Conference on Information and Knowledge Management. 2785–2794.
  38. Optimizing top-n collaborative filtering via dynamic negative item sampling. In Proceedings of the 36th international ACM SIGIR conference on Research and development in information retrieval. 785–788.
  39. Augmented Negative Sampling for Collaborative Filtering. In Proceedings of the 17th ACM Conference on Recommender Systems. 256–266.
  40. A Gain-Tuning Dynamic Negative Sampler for Recommendation. In Proceedings of the ACM Web Conference 2022. 277–285.

Summary

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

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