arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2410.02604cs.IRcs.LG
收藏

长序列推荐模型需要解耦嵌入

Long-Sequence Recommendation Models Need Decoupled Embeddings

Tsinghua University(清华大学);Tencent Inc(腾讯公司)

Ningya Feng, Junwei Pan, Jialong Wu, Baixu Chen, Ximei Wang, Qian Li, Xian Hu, Jie Jiang, Mingsheng Long

AI总结:

针对长序列推荐模型中单一嵌入集导致注意力与表示学习相互干扰的问题,提出解耦注意力与表示嵌入(DARE)模型,通过分离嵌入表提升搜索准确性和AUC,并加速在线服务。

摘要:

在当代推荐系统中,用户长期行为序列对于捕捉用户兴趣和预测用户响应至关重要。通常采用两阶段范式来处理这些长序列:第一阶段通过注意力机制从原始长序列中搜索相关行为的子集,第二阶段将子集与目标物品聚合,构建用于预测的判别性表示。在本工作中,我们首次识别并刻画了现有长序列推荐模型中被忽视的一个缺陷:单一嵌入集难以同时学习注意力和表示,导致这两个过程相互干扰。尝试用一些常见方法(如线性投影——一种从语言处理中借鉴的技术)解决该问题的初步尝试被证明无效,这揭示了推荐模型面临的独特挑战。为克服此问题,我们提出了解耦注意力和表示嵌入(DARE)模型,其中初始化并分别学习两个不同的嵌入表,以完全解耦注意力和表示。大量实验和分析表明,DARE能更准确地搜索相关行为,并在公共数据集上取得高达0.9%的AUC提升,在腾讯广告平台上也有显著改进。此外,解耦嵌入空间使我们能够降低注意力嵌入维度,并将搜索过程加速50%而性能影响不大,从而实现更高效、高性能的在线服务。用于实验(包括模型分析)的PyTorch代码可在https://github.com/thuml/DARE获取。

英文摘要:

Lifelong user behavior sequences are crucial for capturing user interests and predicting user responses in modern recommendation systems. A two-stage paradigm is typically adopted to handle these long sequences: a subset of relevant behaviors is first searched from the original long sequences via an attention mechanism in the first stage and then aggregated with the target item to construct a discriminative representation for prediction in the second stage. In this work, we identify and characterize, for the first time, a neglected deficiency in existing long-sequence recommendation models: a single set of embeddings struggles with learning both attention and representation, leading to interference between these two processes. Initial attempts to address this issue with some common methods (e.g., linear projections -- a technique borrowed from language processing) proved ineffective, shedding light on the unique challenges of recommendation models. To overcome this, we propose the Decoupled Attention and Representation Embeddings (DARE) model, where two distinct embedding tables are initialized and learned separately to fully decouple attention and representation. Extensive experiments and analysis demonstrate that DARE provides more accurate searches of correlated behaviors and outperforms baselines with AUC gains up to 0.9% on public datasets and notable improvements on Tencent's advertising platform. Furthermore, decoupling embedding spaces allows us to reduce the attention embedding dimension and accelerate the search procedure by 50% without significant performance impact, enabling more efficient, high-performance online serving. Code in PyTorch for experiments, including model analysis, is available at https://github.com/thuml/DARE.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑