《计算机应用》唯一官方网站 ›› 2026, Vol. 46 ›› Issue (8): 2477-2484.DOI: 10.11772/j.issn.1001-9081.2025070928

• 数据科学与技术 • 上一篇    下一篇

基于多策略对比学习和自适应标签平滑的文本-ID序列推荐模型

刘珈铭1,2,3, 艾芳菊1,2,3()   

  1. 1.湖北大学 计算机学院,武汉 430062
    2.智慧政务与人工智能应用湖北省工程研究中心(湖北大学),武汉 430062
    3.大数据智能分析与行业应用湖北省重点实验室(湖北大学),武汉 430062
  • 收稿日期:2025-08-14 修回日期:2025-10-31 接受日期:2025-10-31 发布日期:2025-12-22 出版日期:2026-08-10
  • 通讯作者: 艾芳菊
  • 作者简介:刘珈铭(2001—),男,四川广安人,硕士研究生,主要研究方向:自然语言处理、序列推荐
    艾芳菊(1973—),女,湖北武汉人,副教授,博士,主要研究方向:数据挖掘、自然语言处理。
  • 基金资助:
    湖北省自然科学基金青年项目(2023AFB313)

Text-ID sequential recommendation model based on multi-strategy contrastive learning and adaptive label smoothing

Jiaming LIU1,2,3, Fangju AI1,2,3()   

  1. 1.School of Computer Science,Hubei University,Wuhan Hubei 430062,China
    2.Engineering Research Center of Hubei Province in Intelligent Government Affairs and Application of Artificial Intelligence (Hubei University),Wuhan Hubei 430062,China
    3.Hubei Key Laboratory of Big Data Intelligent Analysis and Application (Hubei University),Wuhan Hubei 430062,China
  • Received:2025-08-14 Revised:2025-10-31 Accepted:2025-10-31 Online:2025-12-22 Published:2026-08-10
  • Contact: Fangju AI
  • About author:LIU Jiaming, born in 2001, M. S. candidate. His research interests include natural language processing, sequential recommendation.
  • Supported by:
    Youth Program of Hubei Provincial Natural Science Foundation(2023AFB313)

摘要:

序列推荐系统在捕捉用户兴趣演变方面已取得显著进展,侧信息的有效利用发挥了关键作用,例如将项目的相关文本数据与序列推荐中的项目ID在变换后的域空间进行有效融合,再将这种文本-ID的语义融合用于序列推荐,从而提升推荐性能。针对现有模型面临的用户行为复杂、异构信息融合后的泛化能力有限以及数据稀疏等不足,提出基于多策略对比学习和自适应标签平滑的文本-ID序列推荐模型MCLALS(Multi-strategy Contrastive Learning and Adaptive Label Smoothing)。首先,通过领域专家融合网络处理文本表示,并动态整合不同特征子空间的知识;其次,将处理后的文本表示与ID表示进行序列级语义融合,借助频域变换捕捉异构信息间的深层交互;再次,在融合后的高级表示上应用多策略对比学习,利用多种互补的数据增强策略生成多样化的增强表示,有效缓解数据稀疏性;最后,采用自适应标签平滑机制优化训练目标,增强模型对噪声和长尾分布的鲁棒性。在Food、Office和OR这3个公开基准数据集上对MCLALS进行系统的性能评估。实验结果表明,所提模型在整体性能上优于包括SASRec(Self-Attentive Sequential Recommendation)和TedRec (Text-ID Semantic Fusion for Sequential Recommendation)在内的多个基线模型。其中,在OR数据集上MCLALS的NDCG@10指标相较于最优基线模型至少提升了6.69%,验证了该模型的有效性。

关键词: 序列推荐, 文本-ID融合, 混合专家系统, 多策略对比学习, 自适应标签平滑

Abstract:

Significant progress has been made in sequential recommendation systems for capturing the evolution of user interests, where the effective use of side information plays a crucial role. For example, item-related text data is fused with item ID in sequential recommendation effectively in the transformed domain space, and this text-ID semantic fusion is then used for sequential recommendation, so as to enhance recommendation performance. The existing models suffer from limitations such as the complex user behaviors, limited generalization capability after heterogeneous information fusion, and data sparsity. Therefore, a text-ID sequential recommendation model based on multi-strategy contrastive learning and adaptive label smoothing named MCLALS (Multi-strategy Contrastive Learning and Adaptive Label Smoothing) was proposed. First, textual representations were processed through a domain-expert fusion network and knowledge from different feature subspaces were integrated dynamically. Second, the processed text and ID representations were fused semantically at sequence level through frequency-domain transformation to capture deep interactions among heterogeneous information. Third, on the fused high-level representation, multi-strategy contrastive learning was applied to generate diverse augmented representations using multiple complementary data augmentation strategies, thereby alleviating data sparsity effectively. Finally, adaptive label smoothing was adopted to optimize the training objective, thereby enhancing the model’s robustness to noise and long-tail distribution. MCLALS was evaluated systematically on three public benchmark datasets: Food, Office, and OR. Experimental results show that the proposed model outperforms several baseline models, including SASRec (Self-Attentive Sequential Recommendation) and TedRec (Text-ID Semantic Fusion for Sequential Recommendation), in overall performance. In particular, on the OR dataset, MCLALS achieves at least 6.69% improvement in NDCG@10 compared to the best baseline model, verifying its effectiveness.

Key words: sequential recommendation, text-ID fusion, mixture-of-experts system, multi-strategy contrastive learning, adaptive label smoothing

中图分类号: