A Simple and Robust Ensemble For Click-Through Rate Prediction

被引：0

作者：

Wang, Xingmei ^{[1
]}

Wang, Yankai ^{[1
]}

Lian, Defu ^{[1
]}

机构：

[1] Univ Sci & Technol China, Hefei, Anhui, Peoples R China

来源：

PROCEEDINGS OF WORKSHOP ON THE RECSYS CHALLENGE 2023, RECSYSCHALLENGE 2023 | 2023年

关键词：

recommder systems; deep learning; neural networks;

D O I：

10.1145/3626221.3626231

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper presents the strategy employed by the TOT team, which secured 3rd place in the ACM RecSys Challenge 2023 among academic teams. The challenge, orchestrated by ShareChat, focuses on online advertising and user privacy. The objective is to predict the probability of an application install for each anonymized entry. Our approach, though simple, proves efficient and comprises two primary components: initially, we explore state-of-the-art single-task and multi-task models, and subsequently, we integrate these via a simple yet robust ensemble.

引用

页码：14 / 17

页数：4

共 19 条

[1] AN ANALYSIS OF TRANSFORMATIONS [J].

BOX, GEP ;

COX, DR .

JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-STATISTICAL METHODOLOGY, 1964, 26 (02) :211-252

[2] Enhancing Explicit and Implicit Feature Interactions via Information Sharing for Parallel Deep CTR Models [J].

Chen, Bo ;

Wang, Yichao ;

Liu, Zhirong ;

Tang, Ruiming ;

Guo, Wei ;

Zheng, Hongkun ;

Yao, Weiwei ;

Zhang, Muyu ;

He, Xiuqiang .

PROCEEDINGS OF THE 30TH ACM INTERNATIONAL CONFERENCE ON INFORMATION & KNOWLEDGE MANAGEMENT, CIKM 2021, 2021, :3757-3766

[3] Neural Factorization Machines for Sparse Predictive Analytics [J].

He, Xiangnan ;

Chua, Tat-Seng .

SIGIR'17: PROCEEDINGS OF THE 40TH INTERNATIONAL ACM SIGIR CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION RETRIEVAL, 2017, :355-364

[4]

Hu J, 2018, PROC CVPR IEEE, P7132, DOI [10.1109/TPAMI.2019.2913372, 10.1109/CVPR.2018.00745]

[5] FiBiNET: Combining Feature Importance and Bilinear Feature Interaction for Click-Through Rate Prediction [J].

Huang, Tongwen ;

Zhang, Zhiqi ;

Zhang, Junlin .

RECSYS 2019: 13TH ACM CONFERENCE ON RECOMMENDER SYSTEMS, 2019, :169-177

[6]

Li Y, 2020, INT J COMPUT VISION, V128, P657, DOI [10.1007/978-3-030-01231-1_42, 10.1007/s11263-019-01250-9]

[7] Fi-GNN: Modeling Feature Interactions via Graph Neural Networks for CTR Prediction [J].

Li, Zekun ;

Cui, Zeyu ;

Wu, Shu ;

Zhang, Xiaoyu ;

Wang, Liang .

PROCEEDINGS OF THE 28TH ACM INTERNATIONAL CONFERENCE ON INFORMATION & KNOWLEDGE MANAGEMENT (CIKM '19), 2019, :539-548

[8] RecStudio: Towards a Highly-Modularized Recommender System [J].

Lian, Defu ;

Huang, Xu ;

Chen, Xiaolong ;

Chen, Jin ;

Wang, Xingmei ;

Wang, Yankai ;

Jin, Haoran ;

Fan, Rui ;

Liu, Zheng ;

Wu, Le ;

Chen, Enhong .

PROCEEDINGS OF THE 46TH INTERNATIONAL ACM SIGIR CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION RETRIEVAL, SIGIR 2023, 2023, :2890-2900

[9] xDeepFM: Combining Explicit and Implicit Feature Interactions for Recommender Systems [J].

Lian, Jianxun ;

Zhou, Xiaohuan ;

Zhang, Fuzheng ;

Chen, Zhongxia ;

Xie, Xing ;

Sun, Guangzhong .

KDD'18: PROCEEDINGS OF THE 24TH ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY & DATA MINING, 2018, :1754-1763

[10] Modeling Task Relationships in Multi-task Learning with Multi-gate Mixture-of-Experts [J].

Ma, Jiaqi ;

Zhao, Zhe ;

Yi, Xinyang ;

Chen, Jilin ;

Hong, Lichan ;

Chi, Ed H. .

KDD'18: PROCEEDINGS OF THE 24TH ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY & DATA MINING, 2018, :1930-1939

← 1 2 →