Mixed Negative Sampling for Learning Two-tower Neural Networks in Recommendations

Ji Yang; Xinyang Yi; Derek Zhiyuan Cheng; Lichan Hong; Yang Li; Simon Wang; Taibai Xu; Ed H. Chi

11 captures

11 May 2021 - 05 Sep 2025

Dec	JAN	Feb
	27
2021	2022	2023

success

fail

About this capture

COLLECTED BY

Collection: Twitter Outlinks

This is a Collection of URLs (and Outlinked URLs) extracted from a random feed of 1% of all Tweets.

TIMESTAMPS

The Wayback Machine - http://web.archive.org/web/20220127183359/https://research.google/pubs/pub50257/

Google Research Google Research Logo

Philosophy Research Areas Publications People Tools & Downloads Outreach Careers Blog

Mixed Negative Sampling for Learning Two-tower Neural Networks in Recommendations

●Ji Yang ●Xinyang Yi ●Derek Zhiyuan Cheng ●Lichan Hong ●Yang Li ●Simon Wang ●Taibai Xu ●Ed H. Chi WWW '20: Companion Proceedings of the Web Conference 2020April 2020 (2020) Download Google Scholar Copy Bibtex

Abstract

Learning query and item representations is important for building large scale recommendation systems. In many real applications where there is a huge catalog of items to recommend, the problem of efficiently retrieving top k items given user's query from deep corpus leads to a family of factorized modeling approaches where query and item are jointly embedded into a low-dimensional space. In this paper, we first showcase how to apply a two-tower neural network framework, which is also known as dual encoder in the natural language community, to improve a large-scale, production app recommendation system. Furthermore, we offer a novel negative sampling approach called Mixed Negative Sampling (MNS). In particular, different from commonly used batch or unigram sampling methods, MNS uses a mixture of batch and uniformly sampled negatives to tackle the selection bias of implicit user feedback. We conduct extensive offline experiments in the production dataset and show that MNS outperforms other baseline sampling methods. We also conduct online A/B testing and demonstrate that the two-tower retrieval model based on MNS significantly improves retrieval quality by encouraging more high-quality app installs.

Research Areas

Data Mining and Modeling

Information Retrieval and the Web

Learn more about how we do research

We maintain a portfolio of research projects, providing individuals and teams the freedom to emphasize specific types of work Our Research Philosophy

Privacy Terms About Google Google Products Feedback