Generalization Error Bounds for Two-stage Recommender Systems with Tree Structure

Jin Zhang, Ze Liu, Defu Lian, Enhong Chen

Keywords: Two-stage Recommender Systems, Recommender Systems, Generalization error bounds, Rademacher complexities, Tree-based Learning

Abstract: Two-stage recommender systems play a crucial role in efficiently identifying relevant items and personalizing recommendations from a vast array of options. This paper, based on an error decomposition framework, analyzes the generalization error for two-stage recommender systems with a tree structure, which consist of an efficient tree-based retriever and a more precise yet time-consuming ranker. We use the Rademacher complexity to establish the generalization upper bound for various tree-based retrievers using beam search, as well as for different ranker models under a shifted training distribution. Both theoretical insights and practical experiments on real-world datasets indicate that increasing the branches in tree-based retrievers and harmonizing distributions across stages can enhance the generalization performance of two-stage recommender systems.

Primary Area: Learning theory

Submission Number: 16714