Efficient Cost-Aware Cascade Ranking in Multi-Stage Retrieval

Citations Over TimeTop 1% of 2017 papers

Abstract

Complex machine learning models are now an integral part of modern, large-scale retrieval systems. However, collection size growth continues to outpace advances in efficiency improvements in the learning models which achieve the highest effectiveness. In this paper, we re-examine the importance of tightly integrating feature costs into multi-stage learning-to-rank (LTR) IR systems. We present a novel approach to optimizing cascaded ranking models which can directly leverage a variety of different state-of-the-art LTR rankers such as LambdaMART and Gradient Boosted Decision Trees. Using our cascade model, we conclusively show that feature costs and the number of documents being re-ranked in each stage of the cascade can be balanced to maximize both efficiency and effectiveness. Finally, we also demonstrate that our cascade model can easily be deployed on commonly used collections to achieve state-of-the-art effectiveness results while only using a subset of the features required by the full model.

Related Papers

• → The LambdaLoss Framework for Ranking Metric Optimization(2018)131 cited
• → BoostLR: A Boosting-Based Learning Ensemble for Label Ranking Tasks(2020)19 cited
• → Querywise Fair Learning to Rank through Multi-Objective Optimization(2023)5 cited
• → Bi-Rank: A New Bi-Directional Ranking Method for Goods Selection(2020)1 cited
• → OrdRank: Learning to Rank with Ordered Multiple Hyperplanes(2009)