让大模型生成的推荐向量更均匀，提升推荐效果
ACE: Anisotropy-Controllable Embedding for LLM-enhanced Sequential Recommendation
- 用线性自编码器重塑向量分布，控制方向集中问题
- 在保留语义关系的前提下，使向量更均匀，提升训练稳定性
- 适合做基于大模型的序列推荐系统研究者参考
近期基于LLM作为提取器的推荐方法利用大语言模型将富含语义的物品向量引入序列推荐框架。然而，LLM生成的向量常存在强烈各向异性：多数向量聚集在相似方向，造成几何失衡，难以在微调中适应协同信号。为此，本文提出各向异性可控嵌入（ACE），显式控制LLM生成向量的各向异性。ACE采用线性自编码器（LAE）重构嵌入分布，在保持语义结构的同时，通过L2正则化项控制各维向量的分散程度，降低各向异性；同时重建损失确保物品间语义关系不变。该方法平衡了几何均匀性与语义保真度，实现更稳定的训练。大量实验表明，ACE持续优于现有模型，在Recall@20和NDCG@20上分别提升最高达12.4%和11.8%。
原文摘要 · Abstract (English)
Recent advances in the LLM-as-Extractor paradigm leverage large language models (LLMs) to transfer semantically rich item embeddings into sequential recommendation (SR) backbones. However, LLM-generated embeddings often suffer from strong anisotropy. Most vectors are concentrated in similar directions, resulting in a geometric imbalance that makes it difficult to adapt to collaborative signals during fine-tuning. To address this challenge, we propose Anisotropy-Controllable Embedding (ACE), which explicitly controls the anisotropy of LLM-generated embeddings. Specifically, ACE utilizes a linear autoencoder (LAE) to reshape the embedding distribution while preserving its semantic structure. In this process, the L2-regularization term mitigates the anisotropy by controlling the dispersion of embedding dimensions, while the reconstruction loss maintains semantic relationships among items. That is, ACE balances geometric uniformity and semantic embedding preservation for more stable learning. Extensive experiments demonstrate that ACE consistently outperforms existing LLM-enhanced SR models, yielding improvements of up to 12.4% and 11.8% in Recall@20 and NDCG@20, respectively.
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。