Neighbor Based Enhancement for the Long-Tail Ranking Problem in Video Rank Models
This addresses a common issue in industrial recommender systems, advertising, and search engines where models lose effectiveness for inactive users or items, though it is an incremental improvement over existing methods.
The paper tackles the long-tail ranking problem in video rank models, where user-item interactions are insufficient, by proposing a neighbor enhancement structure that uses similar neighbors with multi-level attention to improve representation training, achieving an absolute CTR AUC gain of 0.0259 on the long-tail user dataset.
Rank models play a key role in industrial recommender systems, advertising, and search engines. Existing works utilize semantic tags and user-item interaction behaviors, e.g., clicks, views, etc., to predict the user interest and the item hidden representation for estimating the user-item preference score. However, these behavior-tag-based models encounter great challenges and reduced effectiveness when user-item interaction activities are insufficient, which we called "the long-tail ranking problem". Existing rank models ignore this problem, but its common and important because any user or item can be long-tailed once they are not consistently active for a short period. In this paper, we propose a novel neighbor enhancement structure to help train the representation of the target user or item. It takes advantage of similar neighbors (static or dynamic similarity) with multi-level attention operations balancing the weights of different neighbors. Experiments on the well-known public dataset MovieLens 1M demonstrate the efficiency of the method over the baseline behavior-tag-based model with an absolute CTR AUC gain of 0.0259 on the long-tail user dataset.