Timezone: »

 
Poster
On Component Interactions in Two-Stage Recommender Systems
Jiri Hron · Karl Krauth · Michael Jordan · Niki Kilbertus

Tue Dec 07 08:30 AM -- 10:00 AM (PST) @
in Poster Session 1 »
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 mere sums of their parts. Such treatment presupposes that the two-stage performance is explained by the behavior of the individual components in isolation. 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 independent nominator training can lead to performance on par with uniformly random recommendations. We find that careful design of item pools, each assigned to a different nominator, alleviates these issues. As manual search for a good pool allocation is difficult, we propose to learn one instead using a Mixture-of-Experts based approach. This significantly improves both precision and recall at $K$.
Keywords: Bandits

Author Information

Jiri Hron (University of Cambridge)
Karl Krauth (UC berkeley)
Michael Jordan (UC Berkeley)
Niki Kilbertus (TUM & Helmholtz AI)

More from the Same Authors