|
|
基于长短期兴趣的深度强化学习推荐模型
|
Abstract:
现有的基于深度学习的推荐模型将推荐过程视为静态过程，在一段时间内使用固定策略进行推荐，难以动态捕捉用户兴趣变化，影响推荐结果的准确性。本文提出了一个利用深度强化学习动态地对推荐过程进行建模的推荐模型，模型以最大化长远收益为目标，通过分别提取长短期序列中的特征信息对用户兴趣进行描述，根据兴趣变化不断改变推荐策略。在Movielens-1m数据集上的实验结果表明，相较于其他基线模型，本文模型可在precision@10和recall@10上分别提升1.7%~7.6%和1.5%~3.8%。
The existing deep learning based recommendation models treat the recommendation process as a static process and use fixed strategies for recommendation over a period of time, which makes it difficult to dynamically capture changes in user interests and affects the accuracy of recommendation results. This article proposes a recommendation model that utilizes deep reinforcement learning to dynamically model the recommendation process. The model aims to maximize long-term benefits and describes user interests by extracting feature information from long and short term sequences. The recommendation strategy is constantly changed according to changes in interest. The experimental results on the Movielens-1m dataset indicate that compared to other baseline models, our model can be applied in precision@10 and recall@10 Increased by 1.7%~7.6% and 1.5%~3.8% respectively.
| [1] | 于蒙, 何文涛, 周绪川, 等. 推荐模型综述[J]. 计算机应用, 2022, 42(6): 1898-1913. |
| [2] | Covington, P., Adams, J. and Sargin, E. (2016) Deep Neural Networks for Youtube Recommendations. Proceedings of the 10th ACM Conference on Recommender Systems, Boston, 15-19 September 2016, 191-198.
https://doi.org/10.1145/2959100.2959190 |
| [3] | He, X., Liao, L., Zhang, H., et al. (2017) Neural Collaborative Fil-tering. Proceedings of the 26th International Conference on World Wide Web, Perth, 3-7 May 2017, 173-182. https://doi.org/10.1145/3038912.3052569 |
| [4] | Zhou, G., Zhu, X., Song, C., et al. (2018) Deep Interest Network for Click-Through Rate Prediction. Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, Cambridge, July 2018, 1059-1068. https://doi.org/10.1145/3219819.3219823 |
| [5] | Chen, H.T., Koc, L., Harmsen, J., et al. (2016) Wide & Deep Learning for Recommender Systems. Proceedings of the 1st Workshop on Deep Learning for Recommender Systems, Boston, 15 September 2016, 7-10.
https://doi.org/10.1145/2988450.2988454 |
| [6] | Guo, H., Tang, R., Ye, Y., et al. (2017) DeepFM: A Factoriza-tion-Machine Based Neural Network for CTR Prediction. Proceedings of the 26th International Joint Conference on Ar-tificial Intelligence, Melbourne, 19-25 August 2017, 1725-1731. https://doi.org/10.24963/ijcai.2017/239 |
| [7] | Zheng, L., Noroozi, V. and Yu, P.S. (2017) Joint Deep Modeling of Users and Items Using Reviews for Recommendation. Proceedings of the 10th ACM International Conference on Web Search and Data Mining, Cambridge, 6-10 February 2017, 425-434. https://doi.org/10.1145/3018661.3018665 |
| [8] | Li, J., Wang, Y. and McAuley, J. (2020) Time In-terval Aware Self-Attention for Sequential Recommendation. Proceedings of the 13th International Conference on Web Search and Data Mining, Houston, 3-7 February 2020, 322-330.
https://doi.org/10.1145/3336191.3371786 |
| [9] | Kang, W.C. and McAuley, J. (2018) Self-Attentive Sequential Recommendation. 2018 IEEE International Conference on Data Mining (ICDM), Singapore, 17-20 November 2018, 197-206. https://doi.org/10.1109/ICDM.2018.00035 |
| [10] | Liu, Q., Zeng, Y., Mokhosi, R., et al. (2018) STAMP: Short-Term Attention/Memory Priority Model for Session-Based Recommendation. Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, London, 19-23 August 2018, 1831-1839. https://doi.org/10.1145/3219819.3219950 |
| [11] | Sun, F., Liu, J., Wu, J., et al. (2019) BERT4Rec: Sequential Rec-ommendation with Bidirectional Encoder Representations from Transformer. Proceedings of the 28th ACM International Conference on Information and Knowledge Management, Beijing, 3-7 November 2019, 1441-1450. https://doi.org/10.1145/3357384.3357895 |
| [12] | Hidasi, B., Karatzoglou, A., Baltrunas, L., et al. (2015) Ses-sion-Based Recommendations with Recurrent Neural Networks. |
| [13] | Mnih, V., Kavukcuoglu, K., Silver, D., et al. (2013) Playing Atari with Deep Reinforcement Learning. Computer Science, 10, 431-439. |
| [14] | Rendle, S. (2010) Fac-torization Machines. 2010 IEEE International Conference on Data Mining, Sydney, 13-17 December 2010, 995-1000. https://doi.org/10.1109/ICDM.2010.127 |
| [15] | 王国霞, 刘贺平. 个性化推荐系统综述[J]. 计算机工程与应用, 2012, 48(7): 66-76. |
