用大模型增强线性自编码器，提升推荐系统文本理解能力
LLM-Enhanced Linear Autoencoders for Recommendation
- 分两阶段优化：先用大模型构建语义关联矩阵，再融合用户行为学习权重
- 在三个数据集上召回率提升27.6%，NDCG提升39.3%
- 闭式解保证高效与全局最优，适合追求性能与速度的推荐系统研究者
大型语言模型（LLMs）被广泛用于丰富推荐系统中文本类物品的信息表征。然而，现有结合文本信息的线性自编码器（LAEs）依赖稀疏的词共现模式，难以捕捉丰富的文本语义。为此，我们提出L3AE，首个将大模型融入LAE框架的方法。L3AE通过两阶段优化策略，有效融合文本语义与用户-物品交互的异构知识：(i) 首先利用大模型生成的物品表征构建语义物品-物品相关矩阵；(ii) 然后从协同信号中学习物品-物品权重矩阵，并将语义相关性作为正则化项进行蒸馏。值得注意的是，每一阶段均采用闭式解优化，确保全局最优与计算高效。大量实验表明，L3AE在三个基准数据集上持续优于现有先进模型，在Recall@20上提升27.6%，NDCG@20上提升39.3%。源代码已公开于https://github.com/jaewan7599/L3AE_CIKM2025。
原文摘要 · Abstract (English)
Large language models (LLMs) have been widely adopted to enrich the semantic representation of textual item information in recommender systems. However, existing linear autoencoders (LAEs) that incorporate textual information rely on sparse word co-occurrence patterns, limiting their ability to capture rich textual semantics. To address this, we propose L3AE, the first integration of LLMs into the LAE framework. L3AE effectively integrates the heterogeneous knowledge of textual semantics and user-item interactions through a two-phase optimization strategy. (i) L3AE first constructs a semantic item-to-item correlation matrix from LLM-derived item representations. (ii) It then learns an item-to-item weight matrix from collaborative signals while distilling semantic item correlations as regularization. Notably, each phase of L3AE is optimized through closed-form solutions, ensuring global optimality and computational efficiency. Extensive experiments demonstrate that L3AE consistently outperforms state-of-the-art LLM-enhanced models on three benchmark datasets, achieving gains of 27.6% in Recall@20 and 39.3% in NDCG@20. The source code is available at https://github.com/jaewan7599/L3AE_CIKM2025.
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。