序列化推荐试图利用用户与物品的历史交互序列,预测下次即将交互的物品。针对序列化推荐中推荐物品依赖于用户的长时间全局兴趣、中时间兴趣还是短时间局部兴趣的不确定性,该文提出了一种基于CW-RNN的多时间尺度序列建模推荐算法。首先,该算法引入CW-RNN层,从用户与物品的历史交互序列中抽取多个时间尺度的用户兴趣特征。然后,通过尺度维卷积来建模对不同时间尺度的用户兴趣特征的依赖,生成多时间尺度用户兴趣特征的统一表示。最后,利用全连接层建模统一的多尺度用户兴趣特征和隐式物品特征的交互关系。在MovieLens-1M和Amazon Movies and TV两个公开数据集上的实验结果表明,相比于现有最优的序列推荐算法,该文提出的算法在准确率上分别提升了3.80%和8.63%。
Abstract
Sequential recommendation attempts to use the historical interaction sequence between users and items to predict the next item to interact with. A multi-scale temporal dynamic model for sequential recommendation with Clockwork RNN is proposed to solve the uncertainty of recommended items by the on users long-term global interest, medium time interest or short time local interest. Firstly, the CW-RNN layer is introduced to extract user’s multi-scale temporal interest features from the historical interaction sequence between users and items. The convolution with CNN on the time scale dimension is then used to learn the user’s interest dependency on different time scales, and generate the user’s unified interest representations. Finally, it uses the fully connected layer to model the interaction between the unified multi-scale user interest representations and item’s embedding representations. Experiments are carried out on MovieLens-1M and Amazon Movies and TV, two public datasets. The results show that our proposed model improves the accuracy by 3.80% and 8.63% respectively compared with the current optimal sequential recommendation algorithms.
关键词
序列推荐 /
多时间尺度 /
动态建模
{{custom_keyword}} /
Key words
sequential recommendation /
multi-temporal scale /
dynamic model
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 陈洁敏, 汤庸, 李建国,等. 个性化推荐算法研究[J]. 华南师范大学学报(自然科学版), 2014, 46(5): 8-15.
[2] 黄立威, 江碧涛, 吕守业,等. 基于深度学习的推荐系统研究综述[J]. 计算机学报, 2018, 41(7): 1619-1647.
[3] Hidasi B, Karatzoglou A, Baltrunas L, et al. Session-based recommendations with recurrent neural networks[C]//Proceedings of the International Conference on Learning Representations, 2016.
[4] Rendle S, Freudenthaler C, Schmidt Thieme L. Factorizing personalized Markov chains for next-basket recommendation[C]//Proceedings of the 19th International Conference on World Wide Web, 2010: 811-820.
[5] Liu Q, Zeng Y, Mokhosi R, et al. STAMP: Short-term attention/memory priority model for session-based recommendation[C]//Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2018: 1831-1839.
[6] Wang P, Guo J, Lan Y, et al. Learning herarchical representation model for next basket recommendation[C]//Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2015: 403-412.
[7] Hihi S E, Bengio Y. Hierarchical recurrent neural networks for long-term dependencies[C]//Proceedings of Neural Information Processing Systems, 1995: 493-499.
[8] Wu Y, Dubois C, Zheng A X, et al. Collaborative denoising auto-encoders for Top-N recommender systems[C]//Proceedings of Web Search and Data Mining, 2016: 153-162.
[9] He X, Liao L, Zhang H, et al. Neural collaborative filtering[C]//Proceedings of the 26th International Conference on World Wide Web, 2017: 173-182.
[10] Ebesu T, Shen B, Fang Y. Collaborative memory network for recommendation systems[C]//Proceedings of the the 41st International ACM SIGIR Conference on Research & Development in Information Retrieval, 2018: 515-524.
[11] Yu F, Liu Q, Wu S, et al. A dynamic recurrent model for next basket recommendation[C]//Proceedings of the International ACM SIGIR Conference on Research and Development in Information Retrieval, 2016: 729-732.
[12] Quadrana M, Karatzoglou A, Hidasi B, et al. Personalizing session-based recommendations with hierarchical recurrent neural networks[C]//Proceedings of the Conference on Recommender Systems, 2017: 130-137.
[13] Zhao W, Wang B, Ye J, et al. Leveraging long and short-term information in content-aware movie recommendation[J]. CoRR, 2017: abs/1712.09059.
[14] Yu L, Zhang C, Liang S, et al. Multi-order attentive ranking model for sequential recommendation[C]//Proceedings of the National Conference on Artificial Intelligence, 2019.
[15] Rendle S, Freudenthaler C, Gantner Z, et al. BPR: Bayesian personalized ranking from implicit feedback[J].Uncertainty in Artificial Intelligence, 2009: 452-461.
[16] Jarvelin K, Kekalainen J. Cumulated gain-based evaluation of IR techniques[J]. Acm Transactions on Information Systems, 2002, 20(4): 422-446.
[17] Lops P, De Ggmmis M, Semeraro G. Content-based recommender systems: State of the art and trends[M]. Recommender Systems Handbook. Boston, MA, Springer US. 2011: 73-105.
[18] Sarwar B, Karypis G, Konstan J, et al. Item-based collaborative filtering recommendation algorithms[C]//Proceedings of the 10th International Conference on World Wide Web, 2001: 285-295.
[19] Burke R. Hybrid Recommender Systems: Survey and Experiments[J]. User Modeling and User-Adapted Interaction, 2002, 12(4): 331-370.
[20] Koutnik J, Greff K, Gomez F J, et al. A Clockwork RNN[C]//Proceedings of the ternational Conference on Machine Learning, 2014: 1863-1871.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家自然科学基金(61602451,11871145)
{{custom_fund}}
PDF(2399 KB)
