用语义捷径过滤噪声，更准捕捉用户真实偏好。
LISRec: Modeling User Preferences with Learned Item Shortcuts for Sequential Recommendation
- 从历史行为中提取个性化语义捷径，聚焦真实兴趣
- 在Yelp和Amazon数据集上推荐效果提升13%
- 适合需要精准长期偏好的推荐场景
用户-物品交互历史对序列推荐至关重要，但常包含误点击等噪声，无法反映真实偏好。为此，我们提出基于学习的物品语义捷径框架LISRec，通过从历史交互中提取个性化的语义捷径，显式建模稳定偏好。LISRec首先学习与任务无关的语义表示以评估物品相似性，进而构建用户所有交互物品的个性化语义图；通过识别图中最大语义连通子集，筛选最具代表性的物品作为语义捷径，指导偏好建模。该聚焦表示能有效过滤无关行为，同时保留真实兴趣的多样性。在Yelp和Amazon Product数据集上的实验表明，LISRec相比基线模型性能提升13%，证明其在捕捉稳定用户兴趣方面的有效性。进一步分析显示，基于捷径的历史记录更能准确反映用户偏好，从而生成更相关、更精准的推荐。代码与数据集已开源：https://github.com/NEUIR/LISRec。
原文摘要 · Abstract (English)
User-item interaction histories are pivotal for sequential recommendation systems but often include noise, such as unintended clicks or actions that fail to reflect genuine user preferences. To address this, we propose Learned Item Shortcuts for Sequential Recommendation (LISRec), a novel framework that explicitly captures stable preferences by extracting personalized semantic shortcuts from historical interactions. LISRec first learns task-agnostic semantic representations to assess item similarities, then constructs a personalized semantic graph over all user-interacted items. By identifying the maximal semantic connectivity subset within this graph, LISRec selects the most representative items as semantic shortcuts to guide user preference modeling. This focused representation filters out irrelevant actions while preserving the diversity of genuine interests. Experimental results on the Yelp and Amazon Product datasets illustrate that LISRec achieves a 13% improvement over baseline recommendation models, showing its effectiveness in capturing stable user interests. Further analysis indicates that shortcut-based histories better capture user preferences, making more accurate and relevant recommendations. All codes and datasets are available at https://github.com/NEUIR/LISRec.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。