计算机科学 ›› 2025, Vol. 52 ›› Issue (11A): 241200062-6.doi: 10.11896/jsjkx.241200062
李博, 莫先
LI Bo, MO Xian
摘要： 随着用户行为偏好的动态变化,传统序列推荐方法面临着难以捕捉用户意图转变的挑战。为了解决这一问题,提出了一种基于引导扩散的序列推荐方法(GDRec),旨在通过将目标项目表示嵌入到扩散模型中,实现对用户当前意图的精准捕捉。具体地,GDRec模型包括以下关键组件:序列编码器、交叉注意力条件去噪解码器和交叉散度目标。序列编码器逐步生成用户偏好表示,捕捉历史序列与当前目标的动态关系;交叉注意力条件去噪解码器去除嵌入表示中的噪声,提高对下一目标项目的预测精度;交叉散度目标则赋予模型排序能力,确保表示的高质量,并在扩散过程中嵌入目标项目表示进行引导。最后,在Amazon的Office和Tools数据集上进行的大量实验证明了GDRec在多个评价指标上均优于现有的先进方法,显示出其在序列推荐任务中的优越性能。此外,消融实验和超参数分析进一步验证了模型的有效性和稳定性。
中图分类号:
| [1]LIU Z,FAN Z,WANG Y,et al.Augmenting sequential recommendation with pseudo-prior items via reversely pre-training transformer [C]//Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval.2021. [2]WANG Y,LIU Z,ZHANG J,et al.DRDT:Dynamic reflectionwith divergent thinking for llm-based sequential recommendation [J].arXiv:2312.1136,2023. [3]WANG Y,ZHANG H,LIU Z,et al.Contrastvae:Contrastive variational autoencoder for sequential recommendation[C]//Proceedings of the 31st ACM International Conference on Information & Knowledge Management.2022. [4]XIE Z,LIU C,ZHANG Y,et al.Adversarial and contrastivevariational autoencoder for sequential recommendation[C]//Proceedings of the Web Conference 2021.2021. [5]KANG W C,MCAULEY J.Self-attentive sequential recommendation[C]//Proceedings of the 2018 IEEE International Confe-rence on Data Mining(ICDM).IEEE,2018. [6]SUN F,LIU J,WU J,et al.BERT4Rec:Sequential recommendation with bidirectional encoder representations from transformer [C]//Proceedings of the 28th ACM International Conference on Information and Knowledge Management.2019. [7]JOZEFOWICZ R,ZAREMBA W,SUTSKEVER I.An empirical exploration of recurrent network architectures [C]//Procee-dings of the International Conference on Machine Learning.PMLR,2015. [8]ZHOU Y,HUANG C,HU Q,et al.Personalized learning full-path recommendation model based on LSTM neural networks [J].Information Sciences,2018,444:135-152. [9]HUANG X,QIAN S,FANG Q,et al.Csan:Contextual self-attention network for user sequential recommendation[C]//Proceedings of the 26th ACM International Conference on Multimedia.2018. [10]CAO Y,ZHANG W,SONG B,et al.Position-aware context attention for session-based recommendation [J].Neurocmputing,2020,376:65-72. [11]QIU R,HUANG Z,YIN H,et al.Contrastive learning for representation degeneration problem in sequential recommendation[C]//Proceedings of the Fifteenth ACM International Confe-rence on Web Search and Data Mining.2022. [12]XIE X,SUN F,LIU Z,et al.Contrastive learning for sequential recommendation[C]//Proceedings of the 2022 IEEE 38th International Conference on Data Engineering(ICDE).IEEE,2022. [13]GUO X,WANG Y,DU T,et al.Contranorm:A contrastivelearning perspective on oversmoothing and beyond [J].arXiv:2302.06562,2023. [14]ZHOU K,WANG H,ZHAO W 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.2020. [15]WANG Y,LIU Z,YANG L,et al.Conditional denoising diffusion for sequential recommendation[C]//Proceedings of the Pacific-Asia Conference on Knowledge Discovery and Data Mi-ning.Springer,2024. [16]RENDLE S,FREUDENTHALER C,SCHMIDT-THIEME L.Factorizing personalized markov chains for next-basket recommendation[C]//Proceedings of the 19th International Confe-rence on World Wide Web.2010. [17]SHANI G,HECKERMAN D,BRAFMAN R I,et al.An MDP-based recommender system [J].The Journal of Machine Lear-ning Research,2005,6(9):1265-1295. [18]ZIMDARS A,CHICKERING D M,MEEK C J A P A.Using temporal data for making recommendations [C]//Proceedings of the 17th Conference on Uncertainty in Artificial Intelligence.2013:580-588. [19]TANG J,WANG K.Personalized top-n sequential recommendation via convolutional sequence embedding[C]//Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining.2018. [20]DING Y,MA Y,WONG W K,et al.Leveraging two types of global graph for sequential fashion recommendation[C]//Proceedings of the 2021 International Conference on Multimedia Retrieval.2021. [21]HO J,JAIN A,ABBEEL P J A I N I P S.Denoising diffusion probabilistic models [J].arXiv:2006.11239,2020. [22]GONG S,LI M,FENG J,et al.Diffuseq:Sequence to sequence text generation with diffusion models [J].arXiv:2210.08933,2022. [23]DU H,YUAN H,HUANG Z,et al.Sequential recommendation with diffusion models [J].arXiv:2304.04541,2023. [24]VASWANI A,SHAZEER N,PARMAR N,et al.Attention isall you need[C∥/Proceedings of the 31st International Confe-rence on Neural Information Processing Systems.2017:6000-6010. [25]OORD A V D,LI Y,VINYALS O J A P A.Representation learning with contrastive predictive coding [J].arXiv:1807.03748,2018. [26]MCAULEY J,TARGETT C,SHI Q,et al.Image-based recommendations on styles and substitutes[C]//Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval.2015. [27]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. [28]HIDASI B,KARATZOGLOU A.Recurrent neural networkswith top-k gains for session-based recommendations[C]//Proceedings of the 27th ACM International Conference on Information and Knowledge Management.2018. |
|
||
首页