In order to improve the recommendation performance of the recommendation model for long-tail items, a general framework DAST (domain adaptation and self-training) which can be integrated into the basic recommendation model is proposed. The framework uses the designed feature transformation module to homogenize the feature distribution of source domain (exposed items) and target domain (unexposed items), introduces the concept of pseudo label, uses the classifier based on data structure relationship to verify the pseudo label of target domain, and further improves the long⁃tail performance by self-training the verified pseudo label. The baseline models before and after integrating DAST framework are compared on Movielens-1M and DIGINETICA datasets. The experimental results show that the long-tail performance of each recommended model has been significantly improved after integrating DAST framework, which proves the universality and effectiveness of this framework.
现有的方法一般通过数据补全[7]、逆倾向得分[8]、引入辅助信息[9]等来解决推荐模型长尾性、推荐多样性不佳的问题。数据补全目前多采用启发式方法,如直接对缺失值填充,但这会导致最后的结果严重依赖于填充数据的准确度;逆倾向得分的方法以倾向得分的无偏估计量为优化目标,效果取决于对倾向得分预测的准确性,且倾向得分在复杂场景中很难被准确估计,因此基于倾向得分的方法在实际应用中较难实现,而且在用户或物品倾斜的情况下还会出现高方差;引入辅助信息的方法往往只能在特定的领域之间使用,通用性较差,无法很好地推广。域自适应技术以及无监督自训练可以充分挖掘现有数据来获得未曝光项目的特征表示,可操作性与通用性好。因此,本文通过融合域自适应技术以及无监督自训练,设计了一个改善推荐模型长尾性能的通用框架DAST(domain adaptation and self-training)。该框架将曝光项目视为源域,未曝光项目视为目标域。域自适应技术主要通过最大平均差异[10]或对抗训练[11]等方法来对齐源域与目标域的特征分布,从而改善推荐模型的长尾性能。本文提出了一种基于特征变换的方法来进行特征分布的对齐并推导出了具体的特征变换公式,同时引入了伪标签的概念,并设计了基于数据结构关系的分类器来对伪标签进行校验,利用未曝光项目高置信度的伪标签进行自训练,以提升模型的类别识别能力。
GUOH F, TANGR M, YEY M, et al. DeepFM: A factorization-machine based neural network for CTR prediction [C]//Proceedings of the 26th International Joint Conference on Artificial Intelligence. California: International Joint Conferences on Artificial Intelligence Organization, 2017: 1725-1731. DOI:10.24963/ijcai.2017/239 .
[2]
XIAOJ, YEH, HEX N, et al. Attentional factorization machines: Learning the weight of feature interactions via attention networks [C]//Proceedings of the 26th International Joint Conference on Artificial Intelligence. California: International Joint Conferences on Artificial Intelligence Organization, 2017: 3119-3125. DOI:10.24963/ijcai.2017/435 .
[3]
ZHOUG R, SONGC R, ZHUX Q, et al. Deep Interest Network for Click-Through Rate Prediction [EB/OL].[2021-08-02]. https://www.researchgate.net/publication/317732664_Deep_Interest_Network_for_Click-Through_Rate_Prediction. DOI: 10.1145/3219819.3219823 .
[4]
KRISHNANA, SHARMAA, SANKARA, et al. An adversarial approach to improve long-tail performance in neural collaborative filtering [C]//Proceedings of the 27th ACM International Conference on Information and Knowledge Management. New York: ACM, 2018: 1491-1494. DOI:10.1145/3269206.3269264 .
[5]
LIUY D, GEK K, ZHANGX, et al. Real-time attention based look-alike model for recommender system[C]//Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. New York: ACM, 2019: 2765-2773. DOI:10.1145/3292500.3330707 .
RENQ J, ZHAOX, HANY. Analysis on the causes of the information cocoons under user perspectives [J]. Library and Information Service, 2021, 65(1): 120-127. DOI:10.13266/j.issn.0252-3116.2021.01.017(Ch ).
[8]
HERNÁNDEZ-LOBATOJ M, HOULSBYN, GHAHRAMANIZ. Probabilistic matrix factorization with non-random missing data [C]// Proceedings of the 31st International Conference on International Conference on Machine Learning. Cambridge: MIT Press, 2014:1512-1520.
[9]
YANGL Q, CUIY, XUANY, et al. Unbiased offline recommender evaluation for missing-not-at-random implicit feedback [C]//Proceedings of the 12th ACM Conference on Recommender Systems. New York: ACM, 2018: 279-287. DOI:10.1145/3240323.3240355 .
[10]
CHENG, CHENX N, FENGF L, et al. Cross-domain recommendation without sharing user-relevant data [C]// International World Wide Web Conferences. New York: Association for Computing Machinery,2019:491-502. DOI:10.1145/3308558.3313538 .
[11]
TZENGE, HOFFMANJ, ZHANGN, et al. Deep domain Confusion: Maximizing for Domain Invariance [EB/OL]. [2014-10-10]. https://arxiv.org/pdf/1412.3474.pdf.
[12]
GALLEGOA J, CALVO-ZARAGOZAJ, FISHERR B. Incremental unsupervised domain-adversarial training of neural networks [J]. IEEE Transactions on Neural Networks and Learning Systems, 2021, 32(11): 4864-4878. DOI:10.1109/tnnls.2020.3025954 .
[13]
XUH R, KOEHNP. Cross-Lingual BERT Contextual Embedding Space Mapping with Isotropic and Isometric Conditions [EB/OL].[2021-08-20].
[14]
CHENZ H, XIAOR, LIC L, et al. ESAM: discriminative domain adaptation with non-displayed items to improve long-tail performance [C]//Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. New York: ACM, 2020: 579-588. DOI:10.1145/3397271.3401043 .
HEX N, LIAOL Z, ZHANGH W, et al. Neural collaborative filtering [C]//Proceedings of the 26th International Conference on World Wide Web. Perth: International World Wide Web Conferences Steering Committee,2017:173-182. DOI: 10.1145/3038912.3052569 .
[17]
CHENQ W, ZHAOH, LIW, et al. Behavior sequence transformer for e-commerce recommendation in Alibaba [C]// Proceedings of the 1st International Workshop on Deep Learning Practice for High⁃Dimensional Sparse Data. New York: Association for Computing Machinery,2019:1-4. DOI: 10.1145/3326937.3341261 .