Welcome to Francis Academic Press

Academic Journal of Computing & Information Science, 2024, 7(1); doi: 10.25236/AJCIS.2024.070103.

Reweighted Attention with Auto Feature Select Gate for CTR Prediction


Chengxu He, Jing Chen

Corresponding Author:
Jing Chen

Guangdong University of Technology, 100 Waihuan Xi Road, Higher Education Mega Center, Guangzhou, 510000, China


CTR (Click-Through-Rate) prediction is an important part of today's recommendation scenarios. Its purpose is to predict whether the user will click on the relevant item.The more mainstream research includes feature interaction and user history behavior interest modeling. However, in some current CTR feature interaction methods, only bit-wise or vector-wise feature interaction is used, or the two-tower approach is used to simply add the output of the two-tower structure at the prediction layer. These methods cannot more comprehensively represent the interaction between features, thus losing a lot of potential feature interaction information.In this paper we propose two novel method:1)Reweighted Attention Network(RAN),which employs vector re-weight after capturing the explicit feature interaction .This module can help model capture the high-order feature potential information more effectively.2)Auto Feature Select Gate(AFSG),which mining potential interactive information of shallow features and higher-order features On the basis of avoiding information loss.Experiments on three public datasets show that our method performs better than the current mainstream CTR prediction models.


Data mining, CTR prediction, Feature interaction, Gate network

Cite This Paper

Chengxu He, Jing Chen. Reweighted Attention with Auto Feature Select Gate for CTR Prediction. Academic Journal of Computing & Information Science (2024), Vol. 7, Issue 1: 18-23. https://doi.org/10.25236/AJCIS.2024.070103.


[1] WANG R,Deep & Cross Network for Ad Click Predictions,in: Proceedings of the ADKDD’17, 2017, pp.1-7.

[2] ZHOU G, Deep Interest Network for Click-Through Rate Prediction,in: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2018,pp. 1059–1068.

[3] SU R, Parallel heterogeneous network with soft gating for CTR prediction,in: Artificial Intelligence. CICAI 2022. Lecture Notes in Computer Science,2022.pp.413-424.

[4] Paul Covington, Deep neural networks for youtube recommendations, In Proceedings of the 10th ACM conference on recommender systems.2016,pp. 191–198.

[5] Huifeng Guo, DeepFM: a factorization-machine based neural network for CTR prediction, In Proceedings of the 26th International Joint Conference on Artificial Intelligence,2016, pp.1725–1731.

[6] LIAN J. xDeepFM: Combining Explicit and Implicit Feature Interactions for Recommender Systems.in: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2018.pp.1754-1763.

[7] W. Song, Autoint: Automatic feature interaction learning via self-attentive neural networks, in: Proceedings of the 28thACM International Conference on Information and Knowledge Management, 2019, pp.1161-1170

[8] S.Rendle, Factorization machines, in: 2010 IEEE International conference on data mining. IEEE,2010,pp.995-1000

[9] ZHAO Z. FINT: Field-aware Interaction Neural Network for CTR Prediction. In: Cornell University - arXiv, 2021,doi: 2107.01999.

[10] HUANG T. GateNet: Gating-Enhanced Deep Network for Click-Through Rate Prediction.in: Cornell University - arXiv: Learning, 2020.doi: 2007.03519.

[11] LU W. A Dual Input-aware Factorization Machine for CTR Prediction.in: Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, 2021, pp.3139-3145.

[12] F. A. Gers, J. Schmidhuber and F. Cummins, Learning to Forget: Continual Prediction with LSTM: in Neural Computation, vol. 12, no. 10, pp. 2451-2471, 1 Oct. 2000, doi: 10.1162/ 089976600300015015.