Rethinking Large-scale Pre-ranking System: Entire-chain Cross-domain Models
arXiv:2310.08039 · doi:10.1145/3511808.3557683
Abstract
Industrial systems such as recommender systems and online advertising, have been widely equipped with multi-stage architectures, which are divided into several cascaded modules, including matching, pre-ranking, ranking and re-ranking. As a critical bridge between matching and ranking, existing pre-ranking approaches mainly endure sample selection bias (SSB) problem owing to ignoring the entire-chain data dependence, resulting in sub-optimal performances. In this paper, we rethink pre-ranking system from the perspective of the entire sample space, and propose Entire-chain Cross-domain Models (ECM), which leverage samples from the whole cascaded stages to effectively alleviate SSB problem. Besides, we design a fine-grained neural structure named ECMM to further improve the pre-ranking accuracy. Specifically, we propose a cross-domain multi-tower neural network to comprehensively predict for each stage result, and introduce the sub-networking routing strategy with regularization to reduce computational costs. Evaluations on real-world large-scale traffic logs demonstrate that our pre-ranking models outperform SOTA methods while time consumption is maintained within an acceptable level, which achieves better trade-off between efficiency and effectiveness.
arXiv comment5 pages, 2 figures
References in corpus (6)
- Embedding-based Retrieval in Facebook Search
- Cascade Ranking for Operational E-commerce Search
- Entire Space Multi-Task Model: An Effective Approach for Estimating Post-Click Conversion Rate
- COLD: Towards the Next Generation of Pre-Ranking System
- MOBIUS: Towards the Next Generation of Query-Ad Matching in Baidu's Sponsored Search
- On Ranking Consistency of Pre-ranking Stage