基于跨域元学习框架的冷启动用户表示学习方法

摘要/Abstract

参考文献

多维度评价

doi:10.6040/j.issn.1672-3961.0.2023.100

摘要： 为解决跨域推荐方法过度依赖重叠用户、在冷启动场景中由于数据稀疏导致泛化能力差两个问题,利用元学习快速适应数据稀疏任务的优势,提出一个基于跨域元学习框架的冷启动用户表示学习方法。设计一个多级注意力融合机制,门控循环单元(gate recurrent unit, GRU)获取用户的短期偏好,多级特征注意力融合源域中用户的长短期偏好,获取用户的广义表示。设计一个元网络训练映射函数的初始化参数,将用户在源域中的偏好转移到目标域,获得冷启动用户在目标域中的初始嵌入表示,并以此进行推荐,取得较好结果。利用亚马逊数据集构建了3个跨域推荐任务并进行广泛试验,试验结果表明,本研究模型在平均绝对误差和均方根误差评价中均优于其他基线模型。

关键词: 跨域推荐, 冷启动推荐, 元学习, 长短期偏好, 多级注意力

中图分类号:

TP399

刘玉芳,王绍卿,郑顺,张丽杰,孙福振. 基于跨域元学习框架的冷启动用户表示学习方法[J]. 山东大学学报 (工学版), 2024, 54(6): 29-37.

LIU Yufang, WANG Shaoqing, ZHENG Shun, ZHANG Lijie, SUN Fuzhen. Cold-start user representation learning method based on cross-domain meta-learning framework[J]. Journal of Shandong University(Engineering Science), 2024, 54(6): 29-37.

[1] WANG C, YU Y, MA W, et al. Towards representation alignment and uniformity in collaborative filtering[C] // Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. New York, USA: Association for Computing Machinery, 2022: 1816-1825.
[2] TALWADKER R, CHAKRABARTY S, PAREEK A, et al. CognitionNet: a collaborative neural network for play style discovery in online skill gaming platform[C] // Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. New York, USA: Association for Computing Machinery, 2022: 3961-3969.
[3] LI J, JING M, LU K, et al. From zero-shot learning to cold-start recommendation[C] //Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence. Honolulu, USA: AAAI Press, 2019: 4189-4196.
[4] ZANG T, ZHU Y, LIU H, et al. A survey on cross-domain recommendation: taxonomies, methods, and future directions[J]. ACM Transactions on Management Information Systems, 2022, 41(2): 1-39.
[5] WANG Jie, YUAN Fajie, CHENG Mingyue, et al. TransRec: learning transferable recommendation from mixture-of-modality feedback[C] //Proceedings of the 8th International Joint Conference. Jinhua, China: Springer, 2024: 193-208.
[6] PAN W. A survey of transfer learning for collaborative recommendation with auxiliary data[J]. Neurocomput, 2016, 177(5): 447-453.
[7] PAN F, LI S, AO X, et al. Warm up cold-start advertisements: improving CTR predictions via learning to learn ID embeddings[C] //Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval. New York, USA: Association for Computing Machinery, 2019: 695-704.
[8] WANG Y, YAO Q, KWOK J. A scalable, adaptive and sound nonconvexregularizer for low-rank matrix learning[C] //Proceedings of the Web Conference 2021. New York, USA: Association for Computing Machinery, 2021: 1798-1808.
[9] DU Z, WANG X, YANG H, et al. Sequential scenario-specific meta learner for online recommendation[C] //Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York, USA: Association for Computing Machinery, 2019: 2895-2904.
[10] ZHANG W, ZHANG P, ZHANG B, et al. A collaborative transfer learning framework for cross-domain recommendation[C] //Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. Long Beach, USA: Association for Computing Machinery, 2023: 2306-16425.
[11] MAN T, SHEN H, JIN X, et al. Cross-domain recommendation: an embedding and mapping approach[C] //Proceedings of the 26th International Joint Conference on Artificial Intelligence. Melbourne, Australia: AAAI Press, 2017: 2464-2470.
[12] KANG S, HWANG J, LEE D, et al. Semi-supervisedlearning for cross-domain recommendation to cold-start users[C] //Proceedings of the 28th ACM International Conference on Information and Knowledge Management. Beijing, China: Association for Computing Machinery, 2019: 1563-1572.
[13] LI P, TUZHILIN A. DDTCDR: deep dual transfer cross domain recommendation[C] //Proceedings of the 13th International Conference on Web Search and Data Mining. New York, USA: Association for Computing Machinery, 2020: 331-339.
[14] BAI T, XIAO Y, WU B, et al. A contrastive sharing model for multi-task recommendation[C] //Proceedings of the ACM Web Conference. New York, USA: Association for Computing Machinery, 2022:3239-3247.
[15] WANG X, HE X, WANG M, et al. Neural graph collaborative filtering[C] //Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval. Paris, France: Association for Computing Machinery, 2019: 165-174.
[16] FARNADI G, TANG J, COCK M D, et al. User profiling through deep multimodal fusion[C] //Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining.New York, USA: Association for Computing Machinery, 2018: 171-179.
[17] ZHU Y, XIE R, ZHUANG F, et al. Learning to warm up cold item embeddings for cold-start recommendation with meta scaling and shifting networks[C] // Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval. New York, USA: Association for Computing Machinery, 2021: 1167-1176.
[18] TRAN T, YOU D, LEE K. Quaternion-based self-attentive long short-term user preference encoding for recommendation[C] //Proceedings of the 29th ACM International Conference on Information and Knowledge Management. New York, USA: Association for Computing Machinery, 2020: 1455-1464.
[19] ZHANG X, LI J, SU H, et al. Multi-level attention-based domain disentanglement for bidirectional cross-domain recommendation[J]. ACM Transactions on Management Information Systems, 2023, 41(4):1046-1070.
[20] TIMOTHY M, ANTREAS A, PAUL M, et al. Meta-learning in neural networks: a survey[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, 44(9): 5149-5169.
[21] LAKE B M. Compositional generalization through meta sequence-to-sequence learning[C] //Proceedings of the 33rd International Conference on Neural Information Processing Systems.New York, USA: Curran Associates Inc., 2019: 9791-9801.
[22] VUORIO R, SUN S H, HU H, et al. Multimodal model-agnostic meta-learning via task-aware modulation[C] //Proceedings of the 33rd International Conference on Neural Information Processing Systems.New York, USA: Curran Associates Inc., 2019: 1-12.
[23] XU H, LI C, ZHANG Y, et al. MetaCAR: cross-domain meta-augmentation for content-aware recom-mendation[J]. IEEE Transactions on Knowledge and Data Engineering, 2023, 35(8): 8199-8212.
[24] RAJESWARAN A, FINN C, KAKADE S M, et al. Meta-learning with implicit gradients[C] //Proceedings of the 33rd International Conference on Neural Information Processing Systems.New York, USA: Curran Associates Inc., 2019: 113-124.
[25] GUAN R, PANG H, GIUNCHIGLIA F, et al. Cross-domain meta-learner for cold-start recommendation[J].IEEE Transactions on Knowledge and Data Engineering, 2023, 35(8): 7829-7843.
[26] LEE H, IM J, IANGS, et al. MeLU: meta-learned user preference estimator for cold-start recommendation[C] //Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York, USA: Association for Computing Machinery, 2019: 1073-1082.
[27] XU M, LIU F, XU W, et al. A survey on sequential recommendation[C] //Proceedings of the 2019 6th International Conference on Information Science and Control Engineering(ICISCE). Shanghai, China: IEEE Computer Society, 2019: 106-111.
[28] DUAN J, ZHANG P, QIU R, et al. Long short-term enhanced memory for sequential recommendation[J]. World Wide Web, 2023, 26(2): 561-583.
[29] SHAW P, USZKOREIT J, VASWANI A. Self-attention with relative position representations[C] //Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguis. New Orleans, USA: Association for Computational Linguistics, 2018: 464-468.
[30] CAI Q, PAN Y, YAO T, et al. Memory matching networks for one-shot image recognition[C] //Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, USA: Computer Vision Foundation, 2018: 4080-4088.
[31] FINN C, ABBEEL P, LEVINE S. Model-agnostic meta-learning for fast adaptation of deep networks[C] // Proceedings of the 34th International Conference on Machine Learning-Volume 70. Sydney, Australia: Journal of Machine Learning Research, 2017:1126-1135.
[32] FU W, PENG Z, WANG S, et al. Deeply fusing reviews and contents for cold start users in cross-domain recommendation systems[C] //Proceedings of the Thirty-Third Conference on Artificial Intelligence. Honolulu, USA: AAAI Press, 2019: 94-101.
[33] ZHU F, WANG Y, CHEN C, et al. A deep framework for cross-domain and cross-system recommendations[C] //Proceedings of the 27th International Joint Conference on Artificial Intelligence. Stockholm, Sweden: AAAI Press, 2018: 3711-3717.
[34] NI J, LI J, MCAULEY J J. Justifying recommendations using distantly-labeled reviews and fine-grained aspects[C] //Proceedings of the 2019 Conference on Empirical Methods in Natural Language. Hong Kong, China: Association for Computational Linguistics, 2019: 188-197.
[35] SINGH A P, GORDON G J. Relational learning via collective matrix factorization[C] //Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Las Vegas, USA: Association for Computing Machinery, 2008: 650-658.
[36] ZHU Y, TANG Z, LIU Y, et al. Personalized transfer of user preferences for cross-domain recommendation[C] // Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining. New York, USA: Association for Computing Machinery, 2022: 1507-1515.
[37] KINGMA D P, BA J. Adam: a method for stochastic optimization[J/OL]. Computer Science.(2015-05-19)[2022-03-13]. http://arxiv.org/abs/1412.6980.

Just accepted

Online first

Just accepted

Online first

Viewed

Full text

From	Others	local

Times	4	53
Rate	7%	93%

Abstract

167

Just accepted	Online first	Issue

0	0	167

From	Others	local

Times	165	3
Rate	98%	2%

Cited

Web of Science	Crossref	ScienceDirect	Search for Citations in Google Scholar >>


This page requires you have already subscribed to WoS.

Shared

Discussed