most citedCOLD: Towards the Next Generation of Pre-Ranking System

10 citations · 18 across the 4 of their papers we have counts for

collaborators

6 papers

cs.LG2021

Real Negatives Matter: Continuous Training with Real Negatives for Delayed Feedback Modeling

Siyu Gu, Xiang-Rong Sheng, Ying Fan +2

One of the difficulties of conversion rate (CVR) prediction is that the conversions can delay and take place long after the clicks. The delayed feedback poses a challenge: fresh da…

cs.IR2021

One Model to Serve All: Star Topology Adaptive Recommender for Multi-Domain CTR Prediction

Xiang-Rong Sheng, Liqin Zhao, Guorui Zhou +8

Traditional industrial recommenders are usually trained on a single business domain and then serve for this domain. However, in large commercial platforms, it is often the case tha…

cs.IR202010 cited

COLD: Towards the Next Generation of Pre-Ranking System

Zhe Wang, Liqin Zhao, Biye Jiang +3

Multi-stage cascade architecture exists widely in many industrial systems such as recommender systems and online advertising, which often consists of sequential modules including m…

cs.IR20205 cited

Search-based User Interest Modeling with Lifelong Sequential Behavior Data for Click-Through Rate Prediction

Pi Qi, Xiaoqiang Zhu, Guorui Zhou +5

Rich user behavior data has been proven to be of great value for click-through rate prediction tasks, especially in industrial applications such as recommender systems and online a…

cs.NI20202 cited

DCAF: A Dynamic Computation Allocation Framework for Online Serving System

Biye Jiang, Pengye Zhang, Rihan Chen +7

Modern large-scale systems such as recommender system and online advertising system are built upon computation-intensive infrastructure. The typical objective in these applications…

cs.IR20201 cited

A Deep Recurrent Survival Model for Unbiased Ranking

Jiarui Jin, Yuchen Fang, Weinan Zhang +7

Position bias is a critical problem in information retrieval when dealing with implicit yet biased user feedback data. Unbiased ranking methods typically rely on causality models a…