Abstract
The data of recommendation systems typically only contain the purchased item as positive data and other un-purchased items as unlabeled data. To train a good recommendation model, in addition to the known positive information, we also need high-quality negative information. Capturing negative signals in positive and unlabeled data is challenging for recommendation systems. Most studies have used specific data and proposed negative sampling methods suitable to the data characteristics. Existing negative sampling strategies cannot automatically select suitable approaches for different data. However, this one-size-fits-all strategy often makes potential positive samples considered as negative, or truly negative samples considered as potential positive samples and recommend to users. In this way, it will not only turn down the recommendation result, but even also have an adverse effect. Accordingly, we propose a novel negative sampling model, Reinforced PU-learning with Hybrid Negative Sampling Strategies for Recommendation (RHNSR), which can combine multiple sampling strategies and dynamically adjust the proportions used by different sampling strategies. In addition, ensemble learning, which integrates various model sampling strategies for obtaining an improved solution, was applied to RHNSR. Extensive experiments were conducted on three real-world recommendation datasets, and the experimental results indicated that the proposed model significantly outperformed state-of-the-art baseline models and revealed significant improvements in precision and hit ratio (49.02% and 37.41%, respectively).
- [1] . 2019. Movie recommender system using K-means clustering and K-nearest neighbor. In Proceedings of the 9th International Conference on Cloud Computing, Data Science & Engineering (Confluence). IEEE, 263–268.Google ScholarCross Ref
- [2] . 2020. Learning from positive and unlabeled data: A survey. Mach. Learn. 109, 4 (2020), 719–760.Google ScholarDigital Library
- [3] . 2016. A random forest guided tour. Test 25, 2 (2016), 197–227.Google ScholarCross Ref
- [4] . 2013. Recommender systems survey. Knowl.-based Syst. 46 (2013), 109–132.Google ScholarDigital Library
- [5] . 2018. Word2vec applied to recommendation: Hyperparameters matter. In Proceedings of the 12th ACM Conference on Recommender Systems. 352–356.Google ScholarDigital Library
- [6] . 2020. Jointly non-sampling learning for knowledge graph enhanced recommendation. In Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. 189–198.Google ScholarDigital Library
- [7] . 2017. 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.Google ScholarDigital Library
- [8] . 2022. Modeling behavior sequence for personalized fund recommendation with graphical deep collaborative filtering. Expert Syst. Applic. 192 (2022), 116311.Google ScholarDigital Library
- [9] . 2015. A robust ensemble approach to learn from positive and unlabeled data using SVM base models. Neurocomputing 160 (2015), 73–84.Google ScholarDigital Library
- [10] . 1995. Fast effective rule induction. In Proceedings of the 12th International Conference on Machine Learning.Google ScholarCross Ref
- [11] . 2018. An improved sampler for Bayesian personalized ranking by leveraging view data. In Proceedings of the the Web Conference. 13–14.Google ScholarDigital Library
- [12] . 2008. Learning classifiers from only positive and unlabeled data. In Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 213–220.Google ScholarDigital Library
- [13] . 2021. Presentation of a recommender system with ensemble learning and graph embedding: A case on MovieLens. Multim. Tools Applic. 80, 5 (2021), 7805–7832.Google ScholarDigital Library
- [14] . 1997. A decision-theoretic generalization of on-line learning and an application to boosting. J. Comput. Syst. Sci. 55, 1 (1997), 119–139.Google ScholarDigital Library
- [15] . 2020. Deep learning for search and recommender systems in practice. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 3515–3516.Google ScholarDigital Library
- [16] . 2019. Deep natural language processing for search and recommender systems. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 3199–3200.Google ScholarDigital Library
- [17] . 2017. Inductive representation learning on large graphs. In Proceedings of the 31st International Conference on Neural Information Processing Systems. 1025–1035.Google ScholarDigital Library
- [18] . 2018. Instance-dependent PU learning by Bayesian optimal relabeling. arXiv preprint arXiv:1808.02180 (2018).Google Scholar
- [19] . 2017. Neural collaborative filtering. In Proceedings of the 26th International Conference on World Wide Web. 173–182.Google ScholarDigital Library
- [20] . 2015. PU learning for matrix completion. In Proceedings of the International Conference on Machine Learning. PMLR, 2445–2453.Google Scholar
- [21] . 2022. Explainable mutual fund recommendation system developed based on knowledge graph embeddings. Appl. Intell. 52, 9 (2022), 10779–10804.Google ScholarDigital Library
- [22] . 2022. Addressing the cold-start problem of recommendation systems for financial products by using few-shot deep learning. Appl. Intell. 52, 13 (2022), 15529–15546.Google ScholarDigital Library
- [23] . 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014).Google Scholar
- [24] . 2016. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016).Google Scholar
- [25] . 2009. Matrix factorization techniques for recommender systems. Computer 42, 8 (2009), 30–37.Google ScholarDigital Library
- [26] . 2014. Acrec: A co-authorship based random walk model for academic collaboration recommendation. In Proceedings of the 23rd International Conference on World Wide Web. 1209–1214.Google Scholar
- [27] . 2016. Bayesian personalized ranking with multi-channel user feedback. In Proceedings of the 10th ACM Conference on Recommender Systems. 361–364.Google ScholarDigital Library
- [28] . 2014. A bagging SVM to learn from positive and unlabeled examples. Pattern Recog. Lett. 37 (2014), 201–209.Google ScholarDigital Library
- [29] . 2020. An investigation on the user interaction modes of conversational recommender systems for the music domain. User Model. User-adapt. Interact. 30, 2 (2020), 251–284.Google ScholarDigital Library
- [30] . 2013. Gradient boosting machines, a tutorial. Front. Neurorobot. 7 (2013), 21.Google ScholarCross Ref
- [31] . 2019. Model-based book recommender systems using naïve bayes enhanced with optimal feature selection. In Proceedings of the 8th International Conference on Software and Computer Applications. 217–222.Google ScholarDigital Library
- [32] . 2017. Learning with confident examples: Rank pruning for robust classification with noisy labels. arXiv preprint arXiv:1705.01936 (2017).Google Scholar
- [33] . 1999. A framework for collaborative, content-based and demographic filtering. Artif. Intell. Rev. 13, 5 (1999), 393–408.Google ScholarDigital Library
- [34] . 2012. BPR: Bayesian personalized ranking from implicit feedback. arXiv preprint arXiv:1205.2618 (2012).Google Scholar
- [35] . 2018. Ensemble learning: A survey. Wiley Interdisc. Rev.: Data Min. Knowl. Discov. 8, 4 (2018), e1249.Google ScholarCross Ref
- [36] . 2009. A survey of collaborative filtering techniques. Adv. Artif. Intell. 2009 (2009), 4.Google ScholarDigital Library
- [37] . 2009. MoviExplain: A recommender system with explanations. In Proceedings of the 3rd ACM Conference on Recommender Systems. 317–320.Google ScholarDigital Library
- [38] . 2018. Bias disparity in recommendation systems. arXiv preprint arXiv:1811.01461 (2018).Google Scholar
- [39] . 2017. Graph attention networks. arXiv preprint arXiv:1710.10903 (2017).Google Scholar
- [40] . 2021. Ensemble learning based classification algorithm recommendation. arXiv preprint arXiv:2101.05993 (2021).Google Scholar
- [41] . 2017. 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.Google ScholarDigital Library
- [42] . 2023. Modeling cross-session information with multi-interest graph neural networks for the next-item recommendation. ACM Trans. Knowl. Discov. Data 17, 1 (2023), 1–28.Google ScholarDigital Library
- [43] . 2019. KGAT: Knowledge graph attention network for recommendation. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 950–958.Google ScholarDigital Library
- [44] . 2020. Reinforced negative sampling over knowledge graph for recommendation. In Proceedings of the Web Conference. 99–109.Google ScholarDigital Library
- [45] . 2020. Graph neural networks in recommender systems: A survey. arXiv preprint arXiv:2011.02260 (2020).Google Scholar
- [46] . 2021. A selective ensemble learning based two-sided cross-domain collaborative filtering algorithm. Inf. Process. Manag. 58, 6 (2021), 102691.Google ScholarDigital Library
- [47] . 2005. A simple probabilistic approach to learning from positive and unlabeled examples. In Proceedings of the 5th Annual UK Workshop on Computational Intelligence (UKCI). 83–87.Google Scholar
- [48] . 2013. 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.Google ScholarDigital Library
Index Terms
- Reinforced PU-learning with Hybrid Negative Sampling Strategies for Recommendation
Recommendations
Revisiting Negative Sampling vs. Non-sampling in Implicit Recommendation
Recommendation systems play an important role in alleviating the information overload issue. Generally, a recommendation model is trained to discern between positive (liked) and negative (disliked) instances for each user. However, under the open-world ...
Reinforced Negative Sampling over Knowledge Graph for Recommendation
WWW '20: Proceedings of The Web Conference 2020Properly handling missing data is a fundamental challenge in recommendation. Most present works perform negative sampling from unobserved data to supply the training of recommender models with negative signals. Nevertheless, existing negative sampling ...
False Negative Sample Aware Negative Sampling for Recommendation
Advances in Knowledge Discovery and Data MiningAbstractNegative sampling plays a key role in implicit feedback collaborative filtering. It draws high-quality negative samples from a large number of uninteracted samples. Existing methods primarily focus on hard negative samples, while overlooking the ...
Comments