On component interactions in two-stage recommender systems

Abstract

Thanks to their scalability, two-stage recommenders are used by many of today's largest online platforms, including YouTube, LinkedIn, and Pinterest. These systems produce recommendations in two steps: (i) multiple nominators-tuned for low prediction latency-preselect a small subset of candidates from the whole item pool; (ii) a slower but more accurate ranker further narrows down the nominated items, and serves to the user. Despite their popularity, the literature on two-stage recommenders is relatively scarce, and the algorithms are often treated as the sum of their parts. Such treatment presupposes that the two-stage performance is explained by the behavior of individual components if they were deployed independently. This is not the case: using synthetic and real-world data, we demonstrate that interactions between the ranker and the nominators substantially affect the overall performance. Motivated by these findings, we derive a generalization lower bound which shows that careful choice of each nominator's training set is sometimes the only difference between a poor and an optimal two-stage recommender. Since searching for a good choice manually is difficult, we learn one instead. In particular, using a Mixture-of-Experts approach, we train the nominators (experts) to specialize on different subsets of the item pool. This significantly improves performance.Preprint. Under review.

Two-Stage Neural Contextual Bandits for Personalised News Recommendation

“…Hierarchical Exploration To address large item spaces, hierarchical search is employed. For two-stage bandits work, Hron et al [10,11] studied the effect of exploration in both two stages with linear bandits algorithms and Mixture-of-Experts nominators. Ma et al [17] proposed off-policy policy-gradient two stage approaches, however, without explicit two-stage exploration.…”