{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/tim4rec-an-efficient-sequential","title":"TiM4Rec: An Efficient Sequential Recommendation Model Based on Time-Aware Structured State Space Duality Model","arxiv_id":"2409.16182","date":"2024-09-24","proceeding":null,"authors":["Hao Fan","Mengyi Zhu","Yanrong Hu","Hailin Feng","ZhiJie He","Hongjiu Liu","Qingyang Liu"],"abstract":"The Sequential Recommendation modeling paradigm is shifting from Transformer to Mamba architecture, which comprises two generations: Mamba1, based on the State Space Model (SSM), and Mamba2, based on State Space Duality (SSD). Although SSD offers superior computational efficiency compared to SSM, it suffers performance degradation in sequential recommendation tasks, especially in low-dimensional scenarios that are critical for these tasks. Considering that time-aware enhancement methods are commonly employed to mitigate performance loss, our analysis reveals that the performance decline of SSD can similarly be fundamentally compensated by leveraging mechanisms in time-aware methods. Thus, we propose integrating time-awareness into the SSD framework to address these performance issues. However, integrating current time-aware methods, modeled after TiSASRec, into SSD faces the following challenges: 1) the complexity of integrating these transformer-based mechanisms with the SSD architecture, and 2) the computational inefficiency caused by the need for dimensionality expansion of time-difference modeling. To overcome these challenges, we introduce a novel Time-aware Structured Masked Matrix that efficiently incorporates time-aware capabilities into SSD. Building on this, we propose Time-Aware Mamba for Recommendation (TiM4Rec), which mitigates performance degradation in low-dimensional SSD contexts while preserving computational efficiency. This marks the inaugural application of a time-aware enhancement method specifically tailored for the Mamba architecture within the domain of sequential recommendation. Extensive experiments conducted on three real-world datasets demonstrate the superiority of our approach. The code for our model is accessible at https://github.com/AlwaysFHao/TiM4Rec.","url_abs":"https://arxiv.org/abs/2409.16182v3","url_pdf":"https://arxiv.org/pdf/2409.16182v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"tim4rec-an-efficient-sequential","repo_url":"https://github.com/alwaysfhao/tim4rec","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"},{"task_slug":"mamba","task_name":"Mamba"},{"task_slug":"recommendation-systems","task_name":"Recommendation Systems"},{"task_slug":"sequential-recommendation","task_name":"Sequential Recommendation"},{"task_slug":"model","task_name":"model"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"mamba","method_name":"Mamba"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"non-maximum-suppression","method_name":"Non Maximum Suppression"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"ssd","method_name":"SSD"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/sequential-recommendation-on-amazon-beauty","task":"Sequential Recommendation","dataset":"Amazon-Beauty","model":"TiM4Rec","rank_in_archive_order":3,"of":3,"metrics":{"HR@10":"0.0854","HR@20":"0.1204","HR@50":"0.18","MRR@10":"0.0321","MRR@20":"0.0345","MRR@50":"0.0363","NDCG@20":"0.0533","NDCG@50":"0.0651","nDCG@10":"0.0446"},"uses_additional_data":false},{"leaderboard":"/sota/sequential-recommendation-on-kuairand","task":"Sequential Recommendation","dataset":"KuaiRand","model":"TiM4Rec","rank_in_archive_order":1,"of":1,"metrics":{"HR@10":"0.1109","HR@20":"0.1774","HR@50":"0.3202","MRR@10":"0.0463","MRR@20":"0.0508","MRR@50":"0.0552","NDCG@10":"0.0611","NDCG@20":"0.0779","NDCG@50":"0.106"},"uses_additional_data":false},{"leaderboard":"/sota/sequential-recommendation-on-movielens-1m","task":"Sequential Recommendation","dataset":"MovieLens 1M","model":"TiM4Rec","rank_in_archive_order":1,"of":4,"metrics":{"HR@10":"0.331","HR@20":"0.4338","HR@5":"0.2308","HR@50":"0.577","MRR@10":"0.1512","MRR@20":"0.1584","MRR@50":"0.1629","NDCG@10":"0.1932","NDCG@20":"0.2194","NDCG@5":"0.1608","NDCG@50":"0.2477"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}