论文标题

NCS4CVR:用于视频转换率预测中多任务学习的神经元连接共享

NCS4CVR: Neuron-Connection Sharing for Multi-Task Learning in Video Conversion Rate Prediction

论文作者

Xiao, Xuanji, Chen, Huabin, Liu, Yuzhen, Yao, Xing, Liu, Pei, Fan, Chaosheng, Ji, Nian, Jiang, Xirong

论文摘要

点击率(CTR)和点击转换率(CVR)预测是工业排名系统中的两个基本模块,例如建议系统,广告和搜索引擎。由于CVR涉及的样本少于CTR(称为CVR数据稀疏问题),因此大多数现有作品都试图利用CTR&CVR多任务学习来提高CVR性能。但是,典型的粗粒子网络/层共享方法可能引入冲突并导致性能降解,因为在CVR和CTR任务之间,并非应共享一层中的每个神经元或神经元连接。这是因为用户可能分别在CVR和CTR表示的深度消耗和点击行为之间具有不同的细粒内容功能偏好。为了解决此共享和冲突问题,我们提出了一种新颖的多任务CVR建模方案,其神经元连接级别共享名为NCS4CVR,它可以自动而灵活地了解没有人工经验的情况下共享哪些神经元权重或不共享哪些神经元。与以前的层级共享方法相比,这是提出在神经元连接级别上的细粒度CTR&CVR共享方法首次提出,这是共享级别的研究范式变化。离线和在线实验都表明,我们的方法的表现都优于单任务模型和层级共享模型。现在,我们提出的方法已成功部署在一个为主要流量服务的行业视频推荐系统中。

Click-through rate (CTR) and post-click conversion rate (CVR) predictions are two fundamental modules in industrial ranking systems such as recommender systems, advertising, and search engines. Since CVR involves much fewer samples than CTR (known as the CVR data sparsity problem), most of the existing works try to leverage CTR&CVR multi-task learning to improve CVR performance. However, typical coarse-grained sub-network/layer sharing methods may introduce conflicts and lead to performance degradation, since not every neuron or neuron connection in one layer should be shared between CVR and CTR tasks. This is because users may have different fine-grained content feature preferences between deep consumption and click behavior, represented by CVR and CTR, respectively. To address this sharing&conflict problem, we propose a novel multi-task CVR modeling scheme with neuron-connection level sharing named NCS4CVR, which can automatically and flexibly learn which neuron weights are shared or not shared without artificial experience. Compared with previous layer-level sharing methods, this is the first time that a fine-grained CTR&CVR sharing method at the neuron connection level is proposed, which is a research paradigm shift in the sharing level. Both offline and online experiments demonstrate that our method outperforms both the single-task model and the layer-level sharing model. Our proposed method has now been successfully deployed in an industry video recommender system serving major traffic.

扫码加入交流群

加入微信交流群

微信交流群二维码

扫码加入学术交流群,获取更多资源