activity
20212023
most citedUnbiased Delayed Feedback Label Correction for Conversion Rate Prediction

11 citations · 15 across the 6 of their papers we have counts for

collaborators
Showing cs.IRShow all

6 papers · 1 filter

cs.IR2023★ 11 cited

Unbiased Delayed Feedback Label Correction for Conversion Rate Prediction

Yifan Wang, Peijie Sun, Min Zhang +3

Conversion rate prediction is critical to many online applications such as digital display advertising. To capture dynamic data distribution, industrial systems often require retra…

cs.IR2023★ 1 cited

Contrastive Multi-view Framework for Customer Lifetime Value Prediction

Chuhan Wu, Jingjie Li, Qinglin Jia +3

Accurate customer lifetime value (LTV) prediction can help service providers optimize their marketing policies in customer-centric applications. However, the heavy sparsity of cons…

cs.IR2022

IntTower: the Next Generation of Two-Tower Model for Pre-Ranking System

Xiangyang Li, Bo Chen, HuiFeng Guo +10

Scoring a large number of candidates precisely in several milliseconds is vital for industrial pre-ranking systems. Existing pre-ranking systems primarily adopt the \textbf{two-tow…

cs.IR2022

Learning Binarized Graph Representations with Multi-faceted Quantization Reinforcement for Top-K Recommendation

Yankai Chen, Huifeng Guo, Yingxue Zhang +4

Learning vectorized embeddings is at the core of various recommender systems for user-item matching. To perform efficient online inference, representation quantization, aiming to e…

cs.IR2021★ 1 cited

Towards Low-loss 1-bit Quantization of User-item Representations for Top-K Recommendation

Yankai Chen, Yifei Zhang, Yingxue Zhang +5

Due to the promising advantages in space compression and inference acceleration, quantized representation learning for recommender systems has become an emerging research direction…

cs.IR2021★ 2 cited

Why Do We Click: Visual Impression-aware News Recommendation

Jiahao Xun, Shengyu Zhang, Zhou Zhao +7

There is a soaring interest in the news recommendation research scenario due to the information overload. To accurately capture users' interests, we propose to model multi-modal fe…