基于多层注意力表示的音乐推荐模型

doi:10.3969/j.issn.0372-2112.2020.09.002

电子学报 ›› 2020, Vol. 48 ›› Issue (9): 1672-1679.DOI: 10.3969/j.issn.0372-2112.2020.09.002

基于多层注意力表示的音乐推荐模型

李琳, 唐守廉

北京邮电大学经济管理学院, 北京 100876

收稿日期:2020-02-05 修回日期:2020-04-09 出版日期:2020-09-25
- 通讯作者:
- 李琳
- 作者简介:
- 唐守廉 男,1952年出生于上海,北京邮电大学经济管理学院教授、博士生导师,主要研究为政府电信管制政策研究,企业发展战略研究,企业市场营销策划.E-mail:tangshoulian@263.net

Hierarchical Attention Representation Model for Music Recommendation

LI Lin, TANG Shou-lian

School of Economics and Management, Beijing University of Posts and Telecommunications, Beijing 100876, China

Received:2020-02-05 Revised:2020-04-09 Online:2020-09-25 Published:2020-09-25
- Corresponding author:
- LI Lin

摘要/Abstract

摘要： 目前的音乐推荐方法只能挖掘用户与歌曲之间的一般性关系，无法区分不同用户对同一首歌曲的差异性偏好.为此，本文提出了基于多层注意力表示的音乐推荐模型，利用用户属性信息和歌曲内容信息从多维度学习歌曲表征，挖掘用户与歌曲之间的偏好关系.为了区分用户对歌曲多域特征的差异性偏好，设计了用户特征依赖的注意力网络；为了区分不同历史行为对用户偏好的差异性，挖掘用户行为的时序依赖关系，设计了歌曲依赖的注意力网络.最后，利用Softmax函数计算用户对候选歌曲的偏好分布并产生推荐.在30Music和MIGU数据集上的实验结果表明，相比目前的推荐模型，本文提出的模型在Recall和MRR均得到了显著提升.

关键词: 特征表示, 注意力网络, 时序关系, 音乐推荐

Abstract: Current music recommendation models can mine the general preference between users and music, which are unable to distinguish the differential preference of different users towards the same song. Therefore, we propose a hierarchical attention representation model (HARM) to improve the music recommendation quality. HARM utilizes attributes of users and contents of music to learn music representation from the perspective of multi-dimension and mine the preference relationship between user and music. In order to mine users' differential preference on music's multi-field feature, a user feature-dependent attention network is designed. In addition, in order to mine the impacts of different historical behavior on user preference and learn sequential dependency of user's, a music-dependent attention network is designed. Finally, recommendation is generated by using a softmax function to calculate the preference distribution of users on candidate songs. The experimental results on 30Music and MIGU datasets shows that, comparing with the existent recommendation models, HARM can gain significant improvement on Recall and MRR.

Key words: feature representation, attention network, sequential relationship, music recommendation

中图分类号:

TP311

李琳, 唐守廉. 基于多层注意力表示的音乐推荐模型[J]. 电子学报, 2020, 48(9): 1672-1679.

LI Lin, TANG Shou-lian . Hierarchical Attention Representation Model for Music Recommendation[J]. Acta Electronica Sinica, 2020, 48(9): 1672-1679.

参考文献

[1] Turrin R,Quadrana M,Condorelli A,et al.30music listening and playlists dataset[A].Proceedings of the 9th ACM Conference on Recommender Systems[C].New York:Association for Computing Machinery,2015.1-4.
[2] 任开旭,王玉龙,刘同存,等.融合多维语义表示的概率矩阵分解模型[J].电子学报,2019,47(9):1848-1854. Ren K X,Wang Y L,Liu T C,et al.A probabilistic matrix factorization model based on multidimensional semantic representation learning[J].Acta Electronica Sinica,2019,47(9):1848-1854.(in Chinese)
[3] Rendle S,Freudenthaler C,Gantner Z,et al.BPR:Bayesian personalized ranking from implicit feedback[A].Proceedings of the Twenty-Fifth Conference on Uncertainty in Artificial Intelligence[C].Virginia:AUAI Press,2009.452-461.
[4] Van den Oord A,Dieleman S,Schrauwen B.Deep content-based music recommendation[A].Advances in Neural Information Processing Systems[C].New York:NIPS,2013.2643-2651.
[5] Dias R,Fonseca M J.Improving music recommendation in session-based collaborative filtering by using temporal context[A].2013 IEEE 25th International Conference on Tools with Artificial Intelligence[C].Piscataway:IEEE,2013.783-788.
[6] Wang D,Deng S,Xu G.Sequence-based context-aware music recommendation[J].Information Retrieval Journal,2018,21(2-3):230-252.
[7] He R,Kang W C,McAuley J.Translation-based recommendation[A].Proceedings of the Eleventh ACM Conference on Recommender Systems[C].New York:Association for Computing Machinery,2017.161-169.
[8] He R,McAuley J.Fusing similarity models with markov chains for sparse sequential recommendation[A].2016 IEEE 16th International Conference on Data Mining (ICDM)[C].Washington:IEEE Computer Society,2016.191-200.
[9] Tavakol M,Brefeld U.Factored MDPs for detecting topics of user sessions[A].Proceedings of the 8th ACM Conference on Recommender Systems[C].New York:Association for Computing Machinery,2014.33-40.
[10] Twardowski B.Modelling contextual information in session-aware recommender systems with neural networks[A].Proceedings of the 10th ACM Conference on Recommender Systems[C].New York:Association for Computing Machinery,2016.273-276.
[11] Kabbur S,Ning X,Karypis G.Fism:factored item similarity models for top-n recommender systems[A].Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining[C].New York:Association for Computing Machinery,2013.659-667.
[12] 潘博,于重重,张青川,等.基于词性与词序的相关因子训练的word2vec改进模型[J].电子学报,2018,46(8):1976-1982. Pan B,Yu C C,Zhang Q C,et al.The improved model for word2vec based on part of speech and word order[J].Acta Electronica Sinica,2018,46(8):1976-1982.(in Chinese)
[13] Hidasi B,Karatzoglou A,Baltrunas L,et al.Session-based recommendations with Recurrent Neural Networks[OL].https://arxiv.org/abs/1511.06939,2015.
[14] Tan Y K,Xu X,Liu Y.Improved recurrent neural networks for session-based recommendations[A].Proceedings of the 1st Workshop on Deep Learning for Recommender Systems[C].New York:Association for Computing Machinery,2016.17-22.
[15] Quadrana M,Karatzoglou A,Personalizing session-based recommendations with hierarchical recurrent neural networks[A].Proceedings of the Eleventh ACM Conference on Recommender Systems[C].New York:Association for Computing Machinery,2017.130-137.
[16] Chatzis S P,Christodoulou P,Andreou A S.Recurrent latent variable networks for session-based recommendation[A].Proceedings of the 2nd Workshop on Deep Learning for Recommender Systems[C].New York:Association for Computing Machinery,2017.38-45.
[17] Wu C,Yan M.Session-aware information embedding for e-commerce product recommendation[A].Proceedings of the 2017 ACM on Conference on Information and Knowledge Management[C].New York:Association for Computing Machinery,2017.2379-2382.
[18] Song Y,Elkahky A M,He X.Multi-rate deep learning for temporal recommendation[A].Proceedings of the 39th International ACM SIGIR Conference on Research and Development in Information Retrieval[C].New York:Association for Computing Machinery,2016.909-912.
[19] Tang J,Wang K.Personalized top-n sequential recommendation via convolutional sequence embedding[A].Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining[C].New York:Association for Computing Machinery,2018.565-573.
[20] 冯建周,宋沙沙,王元卓,等.基于改进注意力机制的实体关系抽取方法[J].电子学报,2019,47(8):1692-1700. Feng J Z,Song S S,Wang Y Z,et al.Entity relation extraction based on improved attention mechanism[J].Acta Electronica Sinica,2019,47(8):1692-1700.(in Chinese)
[21] Li J,Ren P,Chen Z,et al.Neural attentive session-based recommendation[A].Proceedings of the 2017 ACM on Conference on Information and Knowledge Management[C].New York:Association for Computing Machinery,2017.1419-1428.
[22] Liu Q,Zeng Y,Mokhosi R,et al.STAMP:short-term attention/memory priority model for session-based recommendation[A].Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining[C].New York:Association for Computing Machinery,2018.1831-1839.
[23] Sachdeva N,Gupta K,Pudi V.Attentive neural architecture incorporating song features for music recommendation[A].Proceedings of the 12th ACM Conference on Recommender Systems[C].New York:Association for Computing Machinery,2018.417-421.
[24] Zhang S,Tay Y,Yao L,et al.Next Item Recommendation with Self-Attention[OL].https://arxiv.org/abs/1808.06414v2,2018.
[25] Zhou G,Zhu X,Song C,et al.Deep interest network for click-through rate prediction[A].Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining[C].New York:Association for Computing Machinery,2018.1059-1068.
[26] Kang W C,McAuley J.Self-attentive sequential recommendation[A].2018 IEEE International Conference on Data Mining (ICDM)[C].Washington:IEEE Computer Society,2018.197-206.
[27] Goldberg Y,Levy O.word2vec Explained:deriving Mikolov et al.'s negative-sampling word-embedding method[OL].https://arxiv.org/abs/1402.3722v1,2014.

基于多层注意力表示的音乐推荐模型

Hierarchical Attention Representation Model for Music Recommendation

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 9

编辑推荐

Metrics

[1]	丁琪, 田萱, 孙国栋. 基于注意力增强的热点感知新闻推荐模型[J]. 电子学报, 2023, 51(1): 93-104.
[2]	李滔, 董秀成, 林宏伟. 基于深监督跨尺度注意力网络的深度图像超分辨率重建[J]. 电子学报, 2023, 51(1): 128-138.
[3]	李政伟, 李佳树, 尤著宏, 聂茹, 赵欢, 钟堂波. 基于异质图注意力网络的miRNA与疾病关联预测算法[J]. 电子学报, 2022, 50(6): 1428-1435.
[4]	严莉, 张凯, 徐浩, 韩圣亚, 刘珅岐, 史玉良. 基于图注意力机制和Transformer的异常检测[J]. 电子学报, 2022, 50(4): 900-908.
[5]	骈纬国, 吴映波, 陈蒙, 蔡俊鹏. 一种基于时空动态图注意力网络的共享出行需求预测方法[J]. 电子学报, 2022, 50(2): 432-439.
[6]	周勇, 陈思霖, 赵佳琦, 张迪, 王瀚正. 基于弱语义注意力的遥感图像可解释目标检测[J]. 电子学报, 2021, 49(4): 679-689.
[7]	李志欣, 凌锋, 张灿龙, 马慧芳. 融合两级相似度的跨媒体图像文本检索[J]. 电子学报, 2021, 49(2): 268-274.
[8]	李琳, 唐守廉. 融合内容表示的度量排序学习推荐模型[J]. 电子学报, 2020, 48(8): 1615-1622.
[9]	张亚军, 刘宗田, 周文. 基于深度信念网络的事件识别[J]. 电子学报, 2017, 45(6): 1415-1423.