arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.23012cs.IRcs.LG
收藏

基于残差量化连续值预测的序列回归

RQ-Reg: A Residual-Quantization-Based Framework for Continuous Value Prediction in Recommender Systems

Kuaishou Technology(快手科技)

Runpeng Cui, Zhipeng Sun, Chi Lu, Peng Jiang

AI总结:

本文提出基于残差量化的序列学习框架,通过递归预测有序量化代码来提升连续值预测的准确性,实验表明其在推荐系统中的表现优于现有方法。

摘要:

连续值预测在工业级推荐系统中扮演着关键角色,包括预测用户观看时间以及估计电子商务交易的总销售额(GMV)。然而,由于数据分布高度复杂且长尾性质,这一任务仍然具有挑战性。现有的生成方法依赖于刚性的参数分布假设,这种假设从根本上限制了其性能,当这些假设与现实数据不一致时尤为明显。过于简化的形式无法充分建模现实的复杂性,而更复杂的假设则往往面临较差的可扩展性和泛化能力。为了解决这些挑战,我们提出了一种基于残差量化的(RQ)序列学习框架,将目标连续值表示为有序量化代码的总和,这些代码递归地从粗到细的粒度进行预测,随着量化误差逐渐减小。我们引入了一种表示学习目标,使RQ代码嵌入空间与目标值的序结构对齐,使模型能够捕捉量化代码的连续表示,并进一步提高预测准确性。我们在公开基准上对生命周期价值(LTV)和观看时间预测进行了广泛的评估,同时在大型工业短视频推荐平台上进行了大规模的在线实验,用于GMV预测。结果一致显示,我们的方法在性能上优于最先进的方法,并在推荐系统中的各种连续值预测任务中表现出强大的泛化能力。

英文摘要:

Predicting continuous values such as watch-time and gross merchandise value (GMV) is a core problem in industrial recommendation systems. Its inherent difficulty stems from the highly complex and long-tailed distributions of the target signals, which are hard to model accurately. Existing regression methods typically rely on fixed parametric assumptions on the target distribution: overly simple assumptions underfit real-world data, whereas more intricate ones tend to sacrifice scalability and generalization. To address these limitations, we propose a sequence modeling framework based on residual quantization (RQ), in which the target continuous value is decomposed into a sequence of quantization codes that represent progressively finer approximations. The model autoregressively predicts these codes from coarse to fine granularity, with each step refining the residual error left by the previous one. To further improve the quality of the learned representations, we introduce an ordinal-aware representation learning objective that aligns the RQ code embedding space with the ordinal structure of target values, thereby yielding continuous representations of quantization codes and more accurate predictions. We conduct comprehensive experiments on public benchmarks for watch-time and lifetime value (LTV) prediction, together with a large-scale online A/B test for GMV prediction on an industrial short-video recommendation platform. Across all settings, the proposed method shows competitive performance among existing state-of-the-art approaches and generalizes well across diverse continuous value prediction scenarios.

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。

↑