arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2606.01352cs.AI
收藏

FlowTime: 基于流的个性化先验实现连续生成式观看时间预测

FlowTime: Towards Continuous Generative Watch Time Prediction via Flow-based Personalized Priors

Fudan University(复旦大学);Shanghai University of Finance and Economics(上海财经大学);Kuaishou Technology(快手科技);Tongji University(同济大学)

Hongxu Ma, Han Zhou, Chenghou Jin, Jie Zhang, Xiaoyu Yang, Chunjie Chen, Jihong Guan, Shuigeng Zhou

AI总结:

针对现有观看时间预测方法在范式上的局限性,提出连续生成式回归范式及FlowTime方法,利用一步生成变分自编码器和基于流的个性化先验,有效建模多模态用户-物品交互模式,显著提升预测性能。

摘要:

观看时间已成为短视频推荐系统中优化深度用户参与度的关键指标。然而,当前的观看时间预测方法存在固有的范式特定局限性。直接回归因单峰高斯假设而面临均值崩溃,序数回归因刚性离散化而受到量化误差的困扰。同样,离散生成式回归则面临高推理延迟和启发式词汇表设计的问题。除了这些具体缺陷外,一个共同的不足是无法捕捉用户-物品交互模式的内在多模态性和异质性。为应对这些挑战,我们首先从因果角度重新审视观看时间预测问题,并将这些用户特定模式识别为调节观看时间结果的结构性混淆因素,其中相同的兴趣在不同用户习惯条件下表现为不同的观看时间结果。然后,我们正式提出一种新的(即第四种)范式——连续生成式回归,并引入FlowTime,一种利用一步生成变分自编码器的新方法。FlowTime有效规避了迭代去噪的延迟,同时保持了连续潜在空间的表达能力。此外,我们设计了一种基于流的个性化先验,利用归一化流将标准高斯先验扭曲为复杂的历史条件流形,从而实现对多模态交互模式的自适应建模。最后,我们构建了TimeRec,首个开源观看时间预测库,并引入一种新的个性化指标,以建立严格的基准测试标准。广泛的离线实验和在线A/B测试表明,FlowTime显著优于现有最先进方法。

英文摘要:

Watch time has emerged as a pivotal metric for optimizing deep user engagement in short-video recommender systems. However, current methods of watch time prediction (WTP) suffer from inherent paradigm-specific limitations. Direct Regression faces mean-collapse due to unimodal Gaussian assumptions, while Ordinal Regression is hampered by quantization errors from rigid discretization. Similarly, Discrete Generative Regression struggles with high inference latency and heuristic vocabulary design. Beyond these specific flaws, a shared deficiency is the inability to capture the intrinsic multimodality and heterogeneity of User-Item Interaction Patterns. To address these challenges, we first revisit the WTP problem from a causal perspective and identify these user-specific patterns as structural confounders that modulate watch time outcomes, where identical interests manifest as distinct watch time outcomes conditioned on diverse user habits. Then, we formally propose a new (or the fourth) paradigm -- Continuous Generative Regression, and introduce FlowTime, a novel method utilizing a One-step Generative Variational Autoencoder. FlowTime effectively circumvents the latency of iterative denoising while maintaining the expressivity of continuous latent spaces. Furthermore, we design a Flow-based Personalized Prior that leverages NFs to warp a standard Gaussian prior into a complex, history-conditioned manifold, thereby enabling the adaptive modeling of multimodal interaction patterns. Finally, we build TimeRec, the first open-source WTP Library, alongside a novel personalization metric to establish a rigorous benchmarking standard. Extensive offline experiments and online A/B tests demonstrate FlowTime's significant superiority over SOTA methods.

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。

↑