Sequence recommendation aims at item recommendation using users' long and short-term preferences, but most sequence recommendation systems face problems such as insufficient learning power and inadequate fusion of long and short-term preferences. Aiming at the above problems, this paper proposes a fine-grained long and short-term preference sequence recommendation method based on contrastive learning. 1) To address the problem of insufficient long and short-term preference fusion, this paper proposes a long and short-term preference learning layer and a long and short-term preference fusion layer. Firstly, it splits the user behaviour sequence into multi-period sessions and extracts the user's short-term preference in each session by using gated recurrent units, and then fuses the short-term preference sequences to capture the user's long-term preference through the multi-head attention mechanism. Finally, the long-term and short-term preferences are fused adaptively based on the time span to obtain a more representative and comprehensive preference representation. 2) Aiming at the problem of insufficient learning power due to data sparsity, a preference representation comparison learning task is designed to introduce agent user preferences for comparison learning to achieve more accurate preference recommendation. The experimental results show that: compared to the sub-optimal methods, the model improves the Hit@20 metric by 9.84%, 6.40%, and 1.52%, and the MAP@20 metric by 22.64%, 2.42%, and 6.42% on three public datasets, respectively, demonstrating the effectiveness of the proposed method.
FLSR-CL(Fine-grained Long and Short-term preference sequential Recommendation with Contrastive Learning)模型主要由嵌入层、长短期偏好学习层、长短期偏好融合层、对比学习任务4部分组成.1)嵌入层;2)长短期偏好学习层:采用门控循环单元和自注意力机制,分别提取会话中的用户短期偏好,并融合短期偏好生成长期偏好;3)长短期偏好融合层:根据用户当前行为与序列中最后一个行为之间的时间跨度,自适应地在表征维度上对用户的长期与短期偏好进行细粒度融合;4)对比学习任务:引入表征对比学习来最大化长期与短期偏好之间的差异.该模型架构如图1所示.
GaoS, FangJ B, TuQ,et al .Generative news recommendation[C]//Proceedings of the ACM Web Conference 2024,May 13-17,2024,Singapore,Singapore.New York:ACM,2024:3444-3453.
[2]
SaxbornM, PanY C, SaidA .Trust through recommendation in E-commerce[C]//Proceedings of the 2024 Conference on Human Information Interaction and Retrieval,March 10-14,2024,Sheffield,United Kingdom.New York:ACM,2024:87-96.
[3]
QuanY H, DingJ T, GaoC,et al .Alleviating video-length effect for micro-video recommendation[J].ACM Transactions on Information Systems,2023,42(2):44.
[4]
TangJ X, WangK .Personalized top-N sequential recommendation via convolutional sequence embedding[C]//Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining,February 5-9,2018,Marina Del Rey,CA,USA.New York:ACM,2018:565-573.
[5]
YuanF J, KaratzoglouA, ArapakisI,et al .A simple convolutional generative network for next item recommendation[C]//Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining,February 11-15,2019,Melbourne,VIC,Australia.New York:ACM,2019:582-590.
[6]
YanA, ChengS, KangW C,et al .CosRec:2D convolutional neural networks for sequential recommendation[C]//Proceedings of the 28th ACM International Conference on Information and Knowledge Management,November 3-7,2019,Beijing,China.New York:ACM,2019:2173-2176.
[7]
ZhengL, FanZ W, LuC T,et al .Gated spectral units:Modeling co-evolving patterns for sequential recommendation[C]//Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval,July 21-25,2019,Paris,France.New York:ACM,2019:1077-1080.
[8]
SunF, LiuJ, WuJ,et al .BERT4Rec: Sequential recommendation with bidirectional encoder representations from Tranformer[C]//Proceedings of the 28th ACM International Conference on Information and Knowledge Management,November 3-7,2019,Beijing,China.New York:ACM,2019:1441-1450.
[9]
LiJ C, WangY J, McAuleyJ,et al .Time interval aware self-attention for sequential recommendation[C]//Proceedings of the 13th International Conference on Web Search and Data Mining,February 3-7,2020,Houston,TX,USA.New York:ACM,2020:322-330.
[10]
FengY F, LyuF Y, ShenW C,et al .Deep session interest network for click-through rate prediction[C]//Proceedings of the 28th International Joint Conference on Artificial Intelligence,August 10-16,2019,Macao,China.Palo Alto:AAAI Press,2019:2301-2307.
[11]
XieR B, WangY L, WangR,et al .Long short-term temporal meta-learning in online recommendation[C]//Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining,February 21-25,2022,Virtual Event,AZ,USA.New York:ACM,2022:1168-1176.
[12]
AnM X, WuF Z, WuC H,et al .Neural news recommendation with long- and short-term user representations[C]//Procee dings of the 57th Annual Meeting of the Association for Computational Linguistics,July 28-August 2,2019,Florence,Italy.Cambridge:ACL,2019:336-345.
[13]
ZhengY, GaoC, ChangJ X,et al .Disentangling long and short-term interests for recommendation[C]//Proceedings of the ACM Web Conference 2022,April 25-29,2022,Virtual Event,Lyon,France.New York:ACM,2022:2256-2267.
[14]
ArthurJ K, ZhouC H, Osei-KwakyeJ,et al .A heterogeneous couplings and persuasive user/item information model for Next Basket recommendation[J].Engineering Applications of Artificial Intelligence,2022,114:105132.
[15]
LiJ, RenP J, ChenZ M,et al .Neural attentive session-based recommendation[C]//Proceedings of the 2017 ACM on Confe rence on Information and Knowledge Management, November 6-10,2017 ,Singapore,Singapore.New York:ACM,2017:1419-1428.
[16]
ArthurJ K, ZhouC H, ManteyE A,et al .A discriminative-based geometric deep learning model for cross domain recommender systems[J].Applied Sciences,2022,12:5202.
[17]
ZhaoW, WangB Y, YeJ B,et al .PLASTIC:Prioritize long and short-term information in top-n recommendation using adversarial training[C]//Proceedings of the 27th International Joint Conference on Artificial Intelligence,July 13-19,2018,Stockholm,Sweden.Palo Alto:AAAI Press,2018:3676-3682.
[18]
YuZ P, LianJ X, MahmoodyA,et al .Adaptive user modeling with long and short-term preferences for personalized recommendation[C]//Proceedings of the 28th International Joint Conference on Artificial Intelligence,August 10-16,2019,Macao,China.Palo Alto:AAAI Press,2019:4213-4219.
[19]
NiuL S, PengY, LiuY M .Deep recommendation model combining long- and short-term interest preferences[J].IEEE Access,2021,9:166455-166464.
[20]
HeK, LiuQ Y, LiQ M,et al .Long- and short-term sequential recommendation with temporal interval[C]//2022 IEEE Smartworld,Ubiquitous Intelligence & Computing,Scalable Computing & Communications,Digital Twin,Privacy Computing,Metaverse,Autonomous & Trusted Vehicles, December 15-18,2022 ,Haikou,Hainan,China.New York:IEEE,2022:1409-1414.
[21]
YanC R, WangY W, ZhangY T,et al .Modeling long- and short-term user behaviors for sequential recommendation with deep neural networks[C]//2021 International Joint Conference on Neural Networks(IJCNN),July 18-22,2021,Shenzhen,Guangdong,China.New York:IEEE,2021:1-8.
[22]
XieX, SunF, LiuZ Y,et al .Contrastive learning for sequential recommendation[C]//2022 IEEE 38th International Conference on Data Engineering(ICDE),May 9-12,2022,Kuala Lumpur,Malaysia.New York:IEEE,2022:1259-1273.
[23]
YinP, ZhaoJ, MaZ J,et al .Sequential recommendation based on multipair contrastive learning with informative augmenta-tion[J].Neural Computing and Applications,2024,36:9707-9721.
[24]
MaJ X, ZhouC, YangH X,et al .Disentangled self-supervision in sequential recommenders[C]//Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining,August 23-27,2020,Virtual Event,CA,USA.New York:ACM,2020:483-491.
[25]
ZhouK, WangH, ZhaoW X,et al .S3-Rec: Self-supervised learning for sequential recommendation with mutual information maximization[C]//Proceedings of the 29th ACM International Conference on Information & Knowledge Management,October 19-23,2020,Virtual Event,Ireland.New York:ACM,2020:1893-1902.
[26]
HaoY J, ZhangT T, ZhaoP P,et al .Feature-level deeper self-attention network with contrastive learning for sequential recommendation[J].IEEE Transactions on Knowledge and Data Engineering,2023,35(10): 10112-10124.
[27]
Bertin-MahieuxT, EllisD P W, WhitmanB,et al .The million song dataset[C/OL]//ISMIR,2011.
[28]
RuoccoM, SkredeO S L, LangsethH .Inter-session modeling for session-based recommendation[C]//Proceedings of the 2nd Workshop on Deep Learning for Recommender Systems,August 27,2017,Como,Italy.New York:ACM,2017:24-31.
[29]
KangW C, McAuleyJ .Self-attentive sequential recommendation[C]//2018 IEEE International Conference on Data Mi- ning(ICDM), November 17-20,2018 ,Singapore,Singapore.New York:IEEE,2018:197-206.
[30]
LiJ C, WangY J, McAuleyJ .Time interval aware self-attention for sequential recommendation[C]//Proceedings of the 13th International Conference on Web Search and Data Mining,February 3-7,2020,Houston,TX,USA.New York:ACM,2020:322-330.
[31]
ZhangD H, QinJ W, MaJ,et al .Item attributes fusion based on contrastive learning for sequential recommendation[J].Multimedia Systems,2024,30:291.
[32]
RuanS Q, YangC, LiD S .Knowledge-enhanced personalized hierarchical attention network for sequential recommenda-tion[J].World Wide Web,2024,27:2.
[33]
LiY, YangC C, NiT G,et al .Long and short-term interest contrastive learning under filter-enhanced sequential recommendation[J].IEEE Access,2023,11:95928-95938.