0

Feature Generation by Convolutional Neural Network for Click-Through Rate Prediction

FGCNN model automatically generates and combines new features using CNNs and learns interactions with IPNN, significantly improving CTR prediction performance.

Year
2019
Venue
arXiv 2019
Authors
6
Hosting
Abstract onlyARXIV-DEFAULT

Cite

Notes

Only stored in your browser.

Attribution

Abstract & full text
arxiv.org/abs/1904.04447ARXIV-DEFAULT
TL;DR
Semantic Scholar
Attribution policy →

Abstract

Easy-to-use,Modular and Extendible package of deep-learning based CTR models.DeepFM,DeepInterestNetwork(DIN),DeepInterestEvolutionNetwork(DIEN),DeepCrossNetwork(DCN),AttentionalFactorizationMachine(AFM),Neural Factorization Machine(NFM),AutoInt,Deep Session Interest Network(DSIN)

Authors

6