arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2306.03392cs.IR
收藏

用于短视频推荐中观看时长预测的基于树的渐进回归模型

Tree based Progressive Regression Model for Watch-Time Prediction in Short-video Recommendation

Xiao Lin, Xiaokai Chen, Linfeng Song, Jingwei Liu, Biao Li, Peng Jiang

阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出基于树结构的渐进回归模型 TPM，通过有序等级、条件依赖分类、不确定性建模和后门调整提升短视频观看时长预测，并在快手大规模上线验证有效。

摘要：

准确预测观看时长对于提升视频推荐系统中的用户参与度至关重要。为实现这一目标，观看时长预测框架应满足四项特性：首先，尽管观看时长具有连续值，但它同时也是一个有序变量，其取值之间的相对顺序反映了用户偏好的差异。因此，观看时长预测应体现这些序关系。其次，模型应捕捉视频观看行为之间的条件依赖。例如，用户必须先观看视频的一半，然后才能完整观看整个视频。第三，使用点估计对观看时长建模会忽略模型可能给出高不确定性结果这一事实，而这可能在推荐系统中导致糟糕案例。因此，该框架应感知预测不确定性。第四，现实中的推荐系统受到严重偏差放大的影响，因此期望得到不会放大偏差的估计。为此，我们提出用于观看时长预测的 TPM。具体而言，TPM 引入观看时长的有序等级，并将该问题分解为一系列条件依赖的分类任务，这些任务被组织成树结构。通过遍历该树可以生成观看时长的期望，同时观看时长预测的方差作为不确定性度量被显式引入目标函数。此外，我们说明 backdoor adjustment（后门调整）可以无缝融入 TPM，从而缓解偏差放大。我们在公共数据集上进行了大量离线评估，并且 TPM 已部署在 DAU 超过 3 亿的真实视频应用 Kuaishou（快手）中。结果表明，TPM 优于最先进方法，并且确实显著提升了视频消费。

英文摘要：

An accurate prediction of watch time has been of vital importance to enhance user engagement in video recommender systems. To achieve this, there are four properties that a watch time prediction framework should satisfy: first, despite its continuous value, watch time is also an ordinal variable and the relative ordering between its values reflects the differences in user preferences. Therefore the ordinal relations should be reflected in watch time predictions. Second, the conditional dependence between the video-watching behaviors should be captured in the model. For instance, one has to watch half of the video before he/she finishes watching the whole video. Third, modeling watch time with a point estimation ignores the fact that models might give results with high uncertainty and this could cause bad cases in recommender systems. Therefore the framework should be aware of prediction uncertainty. Forth, the real-life recommender systems suffer from severe bias amplifications thus an estimation without bias amplification is expected. Therefore we propose TPM for watch time prediction. Specifically, the ordinal ranks of watch time are introduced into TPM and the problem is decomposed into a series of conditional dependent classification tasks which are organized into a tree structure. The expectation of watch time can be generated by traversing the tree and the variance of watch time predictions is explicitly introduced into the objective function as a measurement for uncertainty. Moreover, we illustrate that backdoor adjustment can be seamlessly incorporated into TPM, which alleviates bias amplifications. Extensive offline evaluations have been conducted in public datasets and TPM have been deployed in a real-world video app Kuaishou with over 300 million DAUs. The results indicate that TPM outperforms state-of-the-art approaches and indeed improves video consumption significantly.

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。

↑