Unsupervised Ranking Ensemble Model for Recommendation

摘要

When visiting an online platform, a user generates various actions, such as clicks, long views, likes, comments, etc. To capture user preferences in these aspects, we learn these objectives and return multiple rankings of candidate items for each user. We need to aggregate them into one to truncate the candidate set, and ranking ensemble model is proposed for this task. However, there is a critical issue: though we input abundant information, what model learns depends on the supervision. Unfortunately, the existing supervision is poorly designed, leading to serious information loss issue. To address this issue, we designed an unsupervised loss to compel the ranking ensemble model to learn all information of input rankings, including sequential and numerical information. (1) For sequential information, we design a distance measure between two rankings, and train the ensemble ranking to have similar order with all input rankings by minimizing the distance. (2) For numerical information, we design a decoder to reconstruct values of original rankings from the hidden layer of the model, to guarantee that the model captures as much input information as possible. Our unsupervised loss is compatible with all ranking ensemble models. We optimize several widely-used structures to propose unsupervised ranking ensemble models. We devise comprehensive experiments on two real-world datasets to demonstrate the effectiveness of the proposed models. We also apply our model in a short video platform with billions of users, and achieve significant improvement.