{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T19:41:50Z","timestamp":1785267710917,"version":"3.55.0"},"reference-count":28,"publisher":"MDPI AG","issue":"10","license":[{"start":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T00:00:00Z","timestamp":1759104000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"The National Social Science Fund of China","award":["24BGL111"],"award-info":[{"award-number":["24BGL111"]}]}],"content-domain":{"domain":["www.mdpi.com"],"crossmark-restriction":true},"short-container-title":["Systems"],"abstract":"<jats:p>Recommender systems are data-driven tools designed to assist or automate users\u2019 decision-making. With the growing demand of personalized sequential recommendations in business intelligence or e-commerce, effectively capturing temporal information from massive user-sequence data has become a crucial challenge. State-of-the-art attention-based models often struggle to balance performance with computational cost, while traditional convolutional neural networks suffer from limited receptive fields and rigid architectures that inadequately model dynamic user interests. To address these limitations, this paper proposes TimeWeaver, a time-aware dual-stream network for sequential recommendation, whose core innovations comprise three key components. First, it employs a re-parameterized large-kernel convolution to expand the effective receptive field. Second, we design a Time-Aware Augmentation mechanism that integrates inter-event time-interval information into positional encodings of items. This allows it to perceive the temporal dynamics of user behavior. Finally, we propose a dual-stream architecture to jointly capture dependencies across different time scales. The context stream employs a modern Temporal Convolutional Network (TCN) structure to strengthen the memorization of users\u2019 medium- and long-term interests. In parallel, the dynamic stream leverages an Exponential Moving Average (EMA) mechanism to weight recent behaviors for sensitively capturing users\u2019 immediate interests. This dual-stream design allows TimeWeaver to comprehensively extract both long- and short-term sequential features. Extensive experiments on three public e-commerce datasets demonstrate TimeWeaver\u2019s superiority. Compared to the strongest baseline model, TimeWeaver achieves average relative improvements of 4.62%, 9.59%, and 4.59% across all metrics on the Beauty, Sports, and Toys datasets, respectively.<\/jats:p>","DOI":"10.3390\/systems13100857","type":"journal-article","created":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T09:12:23Z","timestamp":1759223543000},"page":"857","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["TimeWeaver: Time-Aware Sequential Recommender System via Dual-Stream Temporal Network"],"prefix":"10.3390","volume":"13","author":[{"given":"Yang","family":"Liu","sequence":"first","affiliation":[{"name":"School of Computer and Artificial Intelligence, Nanjing University of Finance and Economics, Nanjing 210023, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tao","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer and Artificial Intelligence, Nanjing University of Finance and Economics, Nanjing 210023, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Ma","sequence":"additional","affiliation":[{"name":"School of Accounting, Nanjing University of Finance and Economics, Nanjing 210023, China"},{"name":"Department of Information Systems and Analytics, National University of Singapore, Singapore 117417, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,9,29]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"102427","DOI":"10.1016\/j.is.2024.102427","article-title":"A survey of sequential recommendation systems: Techniques, evaluation, and future directions","volume":"125","author":"Boka","year":"2024","journal-title":"Inf. Syst."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"He, R., and McAuley, J. (2016, January 12\u201315). Fusing similarity models with markov chains for sparse sequential recommendation. Proceedings of the 2016 IEEE 16th International Conference on Data Mining (ICDM), Barcelona, Spain.","DOI":"10.1109\/ICDM.2016.0030"},{"key":"ref_3","unstructured":"Hidasi, B., Karatzoglou, A., Baltrunas, L., and Tikk, D. (2016, January 2\u20134). Session-based recommendations with recurrent neural networks. Proceedings of the 4th International Conference on Learning Representations (ICLR), San Juan, Puerto Rico."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Tang, J., and Wang, K. (2018, January 5\u20139). Personalized top-n sequential recommendation via convolutional sequence embedding. Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining, Los Angeles, CA, USA.","DOI":"10.1145\/3159652.3159656"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Farha, Y.A., and Gall, J. (2019, January 15\u201320). Ms-tcn: Multi-stage temporal convolutional network for action segmentation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00369"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Yuan, F., Karatzoglou, A., Arapakis, I., Jose, J.M., and He, X. (2019, January 11\u201315). A simple convolutional generative network for next item recommendation. Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining, Melbourne, Australia.","DOI":"10.1145\/3289600.3290975"},{"key":"ref_7","first-page":"5998","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Zhou, K., Yu, H., Zhao, W.X., and Wen, J.R. (2022, January 25\u201329). Filter-enhanced MLP is all you need for sequential recommendation. Proceedings of the ACM Web Conference 2022, Lyon, France.","DOI":"10.1145\/3485447.3512111"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Lara-Ben\u00edtez, P., Carranza-Garc\u00eda, M., Luna-Romera, J.M., and Riquelme, J.C. (2020). Temporal convolutional networks applied to energy-related time series forecasting. Appl. Sci., 10.","DOI":"10.20944\/preprints202003.0096.v1"},{"key":"ref_10","unstructured":"Luo, D., and Wang, X. (2024, January 7\u201311). Moderntcn: A modern pure convolution structure for general time series analysis. Proceedings of the Twelfth International Conference on Learning Representations, Vienna, Austria."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1057\/s41270-023-00274-y","article-title":"Time analysis of online consumer behavior by decision trees, GUHA association rules, and formal concept analysis","volume":"13","author":"Pitka","year":"2025","journal-title":"J. Mark. Anal."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"He, R., Kang, W.C., and McAuley, J. (2017, January 27\u201331). Translation-based recommendation. Proceedings of the Eleventh ACM Conference on Recommender Systems, Como, Italy.","DOI":"10.1145\/3109859.3109882"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Rendle, S., Freudenthaler, C., and Schmidt-Thieme, L. (2010, January 26\u201330). Factorizing personalized markov chains for next-basket recommendation. Proceedings of the 19th International Conference on World Wide Web, Raleigh, NC, USA.","DOI":"10.1145\/1772690.1772773"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Kang, W.C., and McAuley, J. (2018, January 17\u201320). Self-attentive sequential recommendation. Proceedings of the 2018 IEEE International Conference on Data Mining (ICDM), Singapore.","DOI":"10.1109\/ICDM.2018.00035"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Sun, F., Liu, J., Wu, J., Pei, C., Lin, X., Ou, W., and Jiang, P. (2019, January 3\u20137). BERT4Rec: Sequential recommendation with bidirectional encoder representations from transformer. Proceedings of the 28th ACM International Conference on Information and Knowledge management, Beijing, China.","DOI":"10.1145\/3357384.3357895"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3555350","article-title":"Double attention convolutional neural network for sequential recommendation","volume":"16","author":"Chen","year":"2022","journal-title":"ACM Trans. Web"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Jiang, J., Zhang, P., Luo, Y., Li, C., Kim, J.B., Zhang, K., Wang, S., Xie, X., and Kim, S. (2023, January 21\u201325). AdaMCT: Adaptive mixture of CNN-transformer for sequential recommendation. Proceedings of the 32nd ACM International Conference on Information and Knowledge Management, Birmingham, UK.","DOI":"10.1145\/3583780.3614773"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1007\/s11280-024-01291-2","article-title":"A survey on large language models for recommendation","volume":"27","author":"Wu","year":"2024","journal-title":"World Wide Web"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Lin, J., Shan, R., Zhu, C., Du, K., Chen, B., Quan, S., Tang, R., Yu, Y., and Zhang, W. (2024, January 13\u201317). Rella: Retrieval-enhanced large language models for lifelong sequential behavior comprehension in recommendation. Proceedings of the ACM Web Conference 2024, Singapore.","DOI":"10.1145\/3589334.3645467"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Li, J., Wang, Y., and McAuley, J. (2020, January 3\u20137). Time interval aware self-attention for sequential recommendation. Proceedings of the 13th International Conference on Web Search and Data Mining, Houston, TX, USA.","DOI":"10.1145\/3336191.3371786"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Cho, S.M., Park, E., and Yoo, S. (2020, January 22). MEANTIME: Mixture of attention mechanisms with multi-temporal embeddings for sequential recommendation. Proceedings of the 14th ACM Conference on Recommender Systems, Virtual.","DOI":"10.1145\/3383313.3412216"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Cho, J., Hyun, D., Kang, S., and Yu, H. (2021, January 12\u201323). Learning heterogeneous temporal patterns of user preference for timely recommendation. Proceedings of the Web Conference, Virtual.","DOI":"10.1145\/3442381.3449947"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"109894","DOI":"10.1016\/j.asoc.2022.109894","article-title":"A time-aware self-attention based neural network model for sequential recommendation","volume":"133","author":"Zhang","year":"2023","journal-title":"Appl. Soft Comput."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"102936","DOI":"10.1016\/j.ipm.2022.102936","article-title":"Dynamic intent-aware iterative denoising network for session-based recommendation","volume":"59","author":"Zhang","year":"2022","journal-title":"Inf. Process. Manag."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Dang, Y., Yang, E., Guo, G., Jiang, L., Wang, X., Xu, X., Sun, Q., and Liu, H. (2023, January 7\u201314). Uniform sequence better: Time interval aware data augmentation for sequential recommendation. Proceedings of the AAAI Conference on Artificial Intelligence, Washington, DC, USA.","DOI":"10.1609\/aaai.v37i4.25540"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Yue, Z., Wang, Y., He, Z., Zeng, H., McAuley, J., and Wang, D. (2024, January 4\u20138). Linear recurrent units for sequential recommendation. Proceedings of the 17th ACM International Conference on Web Search and Data Mining, M\u00e9rida, Mexico.","DOI":"10.1145\/3616855.3635760"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Li, J., Ren, P., Chen, Z., Ren, Z., Lian, T., and Ma, J. (2017, January 6\u201310). Neural attentive session-based recommendation. Proceedings of the 2017 ACM on Conference on Information and Knowledge Management, Singapore.","DOI":"10.1145\/3132847.3132926"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Jin, D., Jin, Z., Zhou, J.T., and Szolovits, P. (2020, January 20\u201327). Is bert really robust? a strong baseline for natural language attack on text classification and entailment. Proceedings of the AAAI Conference on Artificial Intelligence, Singapore.","DOI":"10.1609\/aaai.v34i05.6311"}],"container-title":["Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2079-8954\/13\/10\/857\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T09:58:00Z","timestamp":1759226280000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2079-8954\/13\/10\/857"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,29]]},"references-count":28,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2025,10]]}},"alternative-id":["systems13100857"],"URL":"https:\/\/doi.org\/10.3390\/systems13100857","relation":{},"ISSN":["2079-8954"],"issn-type":[{"value":"2079-8954","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,29]]}}}