English

Deep Retrieval: Learning A Retrievable Structure for Large-Scale Recommendations

Information Retrieval 2021-05-19 v2 Machine Learning Machine Learning

Abstract

One of the core problems in large-scale recommendations is to retrieve top relevant candidates accurately and efficiently, preferably in sub-linear time. Previous approaches are mostly based on a two-step procedure: first learn an inner-product model, and then use some approximate nearest neighbor (ANN) search algorithm to find top candidates. In this paper, we present Deep Retrieval (DR), to learn a retrievable structure directly with user-item interaction data (e.g. clicks) without resorting to the Euclidean space assumption in ANN algorithms. DR's structure encodes all candidate items into a discrete latent space. Those latent codes for the candidates are model parameters and learnt together with other neural network parameters to maximize the same objective function. With the model learnt, a beam search over the structure is performed to retrieve the top candidates for reranking. Empirically, we first demonstrate that DR, with sub-linear computational complexity, can achieve almost the same accuracy as the brute-force baseline on two public datasets. Moreover, we show that, in a live production recommendation system, a deployed DR approach significantly outperforms a well-tuned ANN baseline in terms of engagement metrics. To the best of our knowledge, DR is among the first non-ANN algorithms successfully deployed at the scale of hundreds of millions of items for industrial recommendation systems.

Keywords

Cite

@article{arxiv.2007.07203,
  title  = {Deep Retrieval: Learning A Retrievable Structure for Large-Scale Recommendations},
  author = {Weihao Gao and Xiangjun Fan and Chong Wang and Jiankai Sun and Kai Jia and Wenzhi Xiao and Ruofan Ding and Xingyan Bin and Hui Yang and Xiaobing Liu},
  journal= {arXiv preprint arXiv:2007.07203},
  year   = {2021}
}

Comments

9 pages, 6 figures

R2 v1 2026-06-23T17:07:04.299Z