LikeSNU 서울대학교 도서관
SNU Big Data Knowledge Information Platform

Full Menu

AI
Report registration
  • Type
  • Title
  • Group
  • Link
  • Thumbnail
Paper List
Paper List (0Count) Export to Excel

There is no data.

CTR 예측을 위한 비전 트랜스포머 활용에 관한 연구

Author
김태석, 김석훈, 임광혁
Journal Title
지식경영연구
Publication Year
2021
Summary

This study presents a method for improving the performance of a transformer model for CTR prediction and analyzes the effect of discrete and categorical CTR data characteristics on model performance. The experimental results confirm that the prediction performance is significantly improved when L2 generalization is applied in the embedding process for CTR data input processing and when batch normalization is applied instead of layer normalization to the transformer model.

Quotation Papers(0)

List of papers cited by this paper

Thesis Indicator

Related Content

LikeSNU analyzes your query semantically to recommend related resources.

Previous
Next

Multi-view improved sequence behavior with adaptive multi-task learning in ranking

Wang, Yingshuai; Zhang, Dezheng; Wulamu, Aziguli · 2023

Applied Intelligence: The International Journal of Research on Intelligent Systems for Real Life Complex Problems

Meta-Wrapper: Differentiable Wrapping Operator for User Interest Selection in CTR Prediction

Cao T.,Xu Q.,Yang Z.,Huang Q. · 2022

IEEE Transactions on Pattern Analysis and Machine Intelligence

Meta-Wrapper: Differentiable Wrapping Operator for User Interest Selection in CTR Prediction

Zhiyong Yang; Qianqian Xu; Qingming Huang; Tianwei Cao · 2021

IEEE Transactions on Pattern Analysis and Machine Intelligence

Previous
Next
TOP