Towards a Better Tradeoff between Effectiveness and Efficiency in Pre-Ranking: A Learnable Feature Selection based Approach

TL;DR

This paper introduces a learnable feature selection method called FSCD for pre-ranking in multi-stage search systems, improving effectiveness without increasing computational costs by supporting complex models.

Contribution

It proposes a novel FSCD method that enables complex interaction-focused models in pre-ranking, balancing effectiveness and efficiency in real-world systems.

Findings

Significant improvement in system effectiveness with FSCD

Maintains computational resource levels comparable to conventional methods

Validated in a real-world e-commerce search system

Abstract

In real-world search, recommendation, and advertising systems, the multi-stage ranking architecture is commonly adopted. Such architecture usually consists of matching, pre-ranking, ranking, and re-ranking stages. In the pre-ranking stage, vector-product based models with representation-focused architecture are commonly adopted to account for system efficiency. However, it brings a significant loss to the effectiveness of the system. In this paper, a novel pre-ranking approach is proposed which supports complicated models with interaction-focused architecture. It achieves a better tradeoff between effectiveness and efficiency by utilizing the proposed learnable Feature Selection method based on feature Complexity and variational Dropout (FSCD). Evaluations in a real-world e-commerce sponsored search system for a search engine demonstrate that utilizing the proposed pre-ranking, the effectiveness of the system is significantly improved. Moreover, compared to the systems with conventional pre-ranking models, an identical amount of computational resource is consumed.