计算机科学 ›› 2022, Vol. 49 ›› Issue (12): 163-169.doi: 10.11896/jsjkx.211200080

• 数据库&大数据&数据科学 • 上一篇    下一篇

用于协同过滤的序列解耦变分自编码器

伍美霖1, 黄佳进2, 秦进1   

  1. 1 贵州大学计算机科学与技术学院 贵阳550025
    2 北京工业大学国际WIC研究院 北京100000
  • 收稿日期:2021-12-06 修回日期:2022-03-25 发布日期:2022-12-14
  • 通讯作者: 黄佳进(jhuang@bjut.edu.cn)
  • 作者简介:(gs.mlwu19@gzu.edu.cn)
  • 基金资助:
    贵州省科学技术基金,黔科合基础([2020]1Y275)

Disentangled Sequential Variational Autoencoder for Collaborative Filtering

WU Mei-lin1, HUANG Jia-jin2, QIN Jin1   

  1. 1 School of Computer Science and Technology,Guizhou University,Guiyang 550025,China
    2 International WIC Institute,Beijing University of Technology,Beijing 100000,China
  • Received:2021-12-06 Revised:2022-03-25 Published:2022-12-14
  • About author:WU Mei-lin,born in 1997,postgra-duate.His main research interests include recommendation system and so on.HUANG Jia-jin,born in 1977,Ph.D.His main research interests include recommendation system and so on.
  • Supported by:
    Guizhou Province Science and Technology Foundation([2020]1Y275).

摘要: 推荐模型通常使用用户的历史行为来获得用户偏好表示,以产生推荐。大多数方法学习到的用户表示会把不同的偏好因素纠缠在一起,而解耦学习的方法可以用于分解用户的行为特征。为此,文中提出了一个基于变分自编码器的框架DSVAECF,用于从用户历史行为中分解静态和动态偏好因素。首先,DSVAECF模型的两个编码器分别使用多层感知机和循环神经网络对用户行为进行历史行为建模,以此得到用户的静态和动态偏好表示;然后,将拼接的静态和动态偏好表示视为用户偏好的解耦表示,并将其输入解码器来捕获用户的决策,并重构出用户行为。在模型训练阶段,一方面最大化重构的用户行为与真实用户行为之间的互信息来学习模型参数;另一方面通过最小化解耦表示与其先验分布间的差异来保留模型的生成能力。在Amazon和MovieLens两个数据集上的实验结果表明,与基准方法相比,DSVAECF在归一化折损累计增益、精确率和召回率上都有显著的提升,拥有更好的推荐性能。

关键词: 变分自编码器, 深度学习, 序列建模, 解耦学习, 协同过滤

Abstract: Recommendation models typically use user’s historical behaviors to obtain user preference representations for recommendations.Most of the methods of learning user representations always entangle different preference factors,while the disentangled learning method can be used to decompose user behavior characteristics.In this paper,a variational autoencoder based framework DSVAECF is proposed to disentangle the static and dynamic factors from user’s historical behaviors.Firstly,two encoders of the model use multi-layer perceptron and recurrent neural network to model the user behavior history respectively,so as to obtain the static and dynamic preference representation of the user.Then,the concatenate static and dynamic preference representations are treated as disentangled representation input decoders to capture user’s decisions and reconstruct user’s behavior.On the one hand,in the model training phase,DSVAECF learns model parameters by maximizes the mutual information between reconstructed user’s behaviors and actual user’s behaviors.On the other hand,DSVAECF minimizes the difference between disentangled representations and their prior distribution to retain the generation ability of the model.Experimental results on Amazon and MovieLens data sets show that,compared with the baselines,DSVAECF significantly improves the normalized discounted cumulative gain,recall,and precision,and has better recommendation performance.

Key words: Variational autoencoder, Deep learning, Sequence modeling, Disentangled learning, Collaborative filtering

中图分类号: 

  • TP391
[1]CHAE D K,KANG J S,KIM S W,et al.Cfgan:A generic collaborative filtering framework based on generative adversarial networks[C]//Proceedings of the 27th ACM International Conference on Information and Knowledge Management.2018:137-146.
[2]KOREN Y,BELL R,VOLINSKY C.Matrix factorization techniques for recommender systems[J].Computer,2009,42(8):30-37.
[3]ZHANG S,YAO L,SUN A,et al.Deep learning based recommender system:A survey and new perspectives[J].ACM Computing Surveys(CSUR),2019,52(1):1-38.
[4]KINGMA D P,WELLING M.Auto-Encoding Variational Bayes[J].arXiv:1312.6114,2013.
[5]REZENDE D J,MOHAMED S,WIERSTRA D.StochasticBackpropagation and Approximate Inference in Deep Generative Models[C]//Proceedings of the International Conference on Machine Learning.PMLR,2014:1278-1286.
[6]WANG S J,HU L,WANG Y,et al.Sequential Recommender Systems:Challenges,Progress and Prospects[C]//Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence{IJCAI-19}.2019.
[7]ZHANG Y,ZHU Z W,HE Y,et al.Content-Collaborative Disentangled representations Learning for Enhanced Recommendation[C]//Proceedings of the Fourteenth ACM Conference on Recommender Systems.2020:43-52.
[8]HE X N,LIAO L Z,ZHANG H W,et al.Neural Collaborative Filtering[C]//Proceedings of the 26th International Conference on World Wide Web.2017:173-182.
[9]HIDASI B,KARATZOGLOU A,BALTRUNAS L,et al.Session-based Recommendations with Recurrent Neural Networks[J].arXiv:1511.06939,2018.
[10]WU C Y,AHMED A,BEUTEL A,et al.Recurrent recommender networks[C]//Proceedings of the Tenth ACM International Conference on Web Search and Data Mining.2017:495-503.
[11]SEDHAIN S,MENON A K,SANNER S,et al.AutoRec:Autoencoders Meet Collaborative Filtering[C]//Proceedings of the 24th International Conference on World Wide Web.2015:111-112.
[12]SHENBIN I,ALEKSEEV A,TUTUBALINA E,et al.Rec-VAE:A new variational autoencoder for Top-N recommendations with implicit feedback[C]//Proceedings of the 13th International Conference on Web Search and Data Mining.2020:528-536.
[13]SACHDEVA N,MANCO G,RITACCO E,et al.Sequential va-riational autoencoders for collaborative filtering[C]//Procee-dings of the Twelfth ACM International Conference on Web Search and Data Mining.2019:600-608.
[14]LIANG D W,KRISHNAN R G,HOFFMAN M D,et al.Variational autoencoders for collaborative filtering[C]//Proceedings of the 2018 World wide Web Conference.2018:689-698.
[15]LI Y Z,MANDT S.Disentangled sequential autoencoder[C]//Proceedings of the 35th International Conference on Machine Learning.2018:5656-5665.
[16]HAN J,MIN M R,HAN L,et al.Disentangled recurrent wasser-stein autoencoder[C]//Proceedings of the 2021 International Conference on Learning Representations.2021.
[17]BAI J W,WANG W R,CARLA P G.Contrastively disentangled sequential variational autoencoder[C]//Proceedings of the 2021 Annual Conferenceon Neural Information Processing Systems.2021.
[18]HAN J,MIN M R,HAN L G,et al.Disentangled RecurrentWasserstein Autoencoder[C]//Proceedings of the 9th International Conference on Learning Representations.2020.
[19]BOWMAN S R,VILNIS L,VINYALS O,et al.Generating sentences from a continuous space[C]//Proceedings of the 20th SIGNLL Conference on Computational Natural Language Learning,CoNLL.Association for Computational Linguistics(ACL),2016:10-21.
[20]TOLSTIKHIN I,BOUSQUET O,GELLY S,et al.Wasserstein auto-encoders[C]//Proceedings of the 6th International Confe-rence on Learning Representations(ICLR 2018).OpenReview.net,2018.
[21]KABBUR S,NING X,KARYPIS G.FISM:Factored Item Similarity Models for top-N Recommender Systems[C]//Procee-dings of the 19th ACM SIGKDD International.2013:659-667.
[1] 程章桃, 钟婷, 张晟铭, 周帆.
基于图学习的推荐系统研究综述
Survey of Recommender Systems Based on Graph Learning
计算机科学, 2022, 49(9): 1-13. https://doi.org/10.11896/jsjkx.210900072
[2] 王冠宇, 钟婷, 冯宇, 周帆.
基于矢量量化编码的协同过滤推荐方法
Collaborative Filtering Recommendation Method Based on Vector Quantization Coding
计算机科学, 2022, 49(9): 48-54. https://doi.org/10.11896/jsjkx.210700109
[3] 徐涌鑫, 赵俊峰, 王亚沙, 谢冰, 杨恺.
时序知识图谱表示学习
Temporal Knowledge Graph Representation Learning
计算机科学, 2022, 49(9): 162-171. https://doi.org/10.11896/jsjkx.220500204
[4] 饶志双, 贾真, 张凡, 李天瑞.
基于Key-Value关联记忆网络的知识图谱问答方法
Key-Value Relational Memory Networks for Question Answering over Knowledge Graph
计算机科学, 2022, 49(9): 202-207. https://doi.org/10.11896/jsjkx.220300277
[5] 汤凌韬, 王迪, 张鲁飞, 刘盛云.
基于安全多方计算和差分隐私的联邦学习方案
Federated Learning Scheme Based on Secure Multi-party Computation and Differential Privacy
计算机科学, 2022, 49(9): 297-305. https://doi.org/10.11896/jsjkx.210800108
[6] 孙奇, 吉根林, 张杰.
基于非局部注意力生成对抗网络的视频异常事件检测方法
Non-local Attention Based Generative Adversarial Network for Video Abnormal Event Detection
计算机科学, 2022, 49(8): 172-177. https://doi.org/10.11896/jsjkx.210600061
[7] 王剑, 彭雨琦, 赵宇斐, 杨健.
基于深度学习的社交网络舆情信息抽取方法综述
Survey of Social Network Public Opinion Information Extraction Based on Deep Learning
计算机科学, 2022, 49(8): 279-293. https://doi.org/10.11896/jsjkx.220300099
[8] 郝志荣, 陈龙, 黄嘉成.
面向文本分类的类别区分式通用对抗攻击方法
Class Discriminative Universal Adversarial Attack for Text Classification
计算机科学, 2022, 49(8): 323-329. https://doi.org/10.11896/jsjkx.220200077
[9] 姜梦函, 李邵梅, 郑洪浩, 张建朋.
基于改进位置编码的谣言检测模型
Rumor Detection Model Based on Improved Position Embedding
计算机科学, 2022, 49(8): 330-335. https://doi.org/10.11896/jsjkx.210600046
[10] 孙晓寒, 张莉.
基于评分区域子空间的协同过滤推荐算法
Collaborative Filtering Recommendation Algorithm Based on Rating Region Subspace
计算机科学, 2022, 49(7): 50-56. https://doi.org/10.11896/jsjkx.210600062
[11] 胡艳羽, 赵龙, 董祥军.
一种用于癌症分类的两阶段深度特征选择提取算法
Two-stage Deep Feature Selection Extraction Algorithm for Cancer Classification
计算机科学, 2022, 49(7): 73-78. https://doi.org/10.11896/jsjkx.210500092
[12] 程成, 降爱莲.
基于多路径特征提取的实时语义分割方法
Real-time Semantic Segmentation Method Based on Multi-path Feature Extraction
计算机科学, 2022, 49(7): 120-126. https://doi.org/10.11896/jsjkx.210500157
[13] 侯钰涛, 阿布都克力木·阿布力孜, 哈里旦木·阿布都克里木.
中文预训练模型研究进展
Advances in Chinese Pre-training Models
计算机科学, 2022, 49(7): 148-163. https://doi.org/10.11896/jsjkx.211200018
[14] 周慧, 施皓晨, 屠要峰, 黄圣君.
基于主动采样的深度鲁棒神经网络学习
Robust Deep Neural Network Learning Based on Active Sampling
计算机科学, 2022, 49(7): 164-169. https://doi.org/10.11896/jsjkx.210600044
[15] 苏丹宁, 曹桂涛, 王燕楠, 王宏, 任赫.
小样本雷达辐射源识别的深度学习方法综述
Survey of Deep Learning for Radar Emitter Identification Based on Small Sample
计算机科学, 2022, 49(7): 226-235. https://doi.org/10.11896/jsjkx.210600138
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!