2021年CTR论文泛读

SIGIR'21

A General Method For Automatic Discovery of Powerful Interactions In Click-Through Rate Prediction

• 自动发掘特征交互方法

Deep User Match Network for Click-Through Rate Prediction

• measures the user-to-user relevance for CTR prediction

RLNF: Reinforcement Learning based Noise Filtering for Click-Through Rate Prediction

• 利用强化学习筛选负样本

GateNet:Gating-Enhanced Deep Network for Click-Through Rate Prediction

KDD'21

Dual Graph enhanced Embedding Neural Network for CTR Prediction

Dual Attentive Sequential Learning for Cross-Domain Click-Through Rate Prediction

WWW'21

DCN V2: Improved Deep & Cross Network and Practical Lessons for Web-scale Learning to Rank Systems

CIKM'21

Enhancing Explicit and Implicit Feature Interactions via Information Sharing for Parallel Deep CTR Models

WSDM'21

DeepLight: Deep Lightweight Feature Interactions for Accelerating CTR Predictions in Ad Serving

PAKDD'21

XCrossNet: Feature Structure-Oriented Learning for Click-Through Rate Prediction