ABSTRACT
Click-Through Rate (CTR) prediction is critical for industrial recommender systems, where most deep CTR models follow an Embedding & Feature Interaction paradigm. However, the majority of methods focus on designing network architectures to better capture feature interactions while the feature embedding, especially for numerical features, has been overlooked. Existing approaches for numerical features are difficult to capture informative knowledge because of the low capacity or hard discretization based on the offline expertise feature engineering. In this paper, we propose a novel embedding learning framework for numerical features in CTR prediction (AutoDis) with high model capacity, end-to-end training and unique representation properties preserved. AutoDis consists of three core components: meta-embeddings, automatic discretization and aggregation. Specifically, we propose meta-embeddings for each numerical field to learn global knowledge from the perspective of field with a manageable number of parameters. Then the differentiable automatic discretization performs soft discretization and captures the correlations between the numerical features and meta-embeddings. Finally, distinctive and informative embeddings are learned via an aggregation function. Comprehensive experiments on two public and one industrial datasets are conducted to validate the effectiveness of AutoDis. Moreover, AutoDis has been deployed onto a mainstream advertising platform, where online A/B test demonstrates the improvement over the base model by 2.1% and 2.7% in terms of CTR and eCPM, respectively. In addition, the code of our framework is publicly available in MindSpore.
- 2020. MindSpore. https://www.mindspore.cn/Google Scholar
- Heng-Tze Cheng, Levent Koc, Jeremiah Harmsen, Tal Shaked, Tushar Chandra, Hrishi Aradhye, Glen Anderson, Greg Corrado, Wei Chai, Mustafa Ispir, Rohan Anil, Zakaria Haque, Lichan Hong, Vihan Jain, Xiaobing Liu, and Hemal Shah. 2016. Wide & Deep Learning for Recommender Systems. In Proc. Workshop Deep Learning for Recommender Systems.Google ScholarDigital Library
- Paul Covington, Jay Adams, and Emre Sargin. 2016. Deep Neural Networks for YouTube Recommendations. In RecSys.Google Scholar
- Antonio Ginart, Maxim Naumov, Dheevatsa Mudigere, Jiyan Yang, and James Zou. 2019. Mixed dimension embeddings with application to memory-efficient recommendation systems. arXiv preprint arXiv:1909.11810 (2019).Google Scholar
- Krzysztof Grabczewski and Norbert Jankowski. 2005. Feature Selection with Decision Tree Criterion. In HIS. IEEE Computer Society, 212--217.Google Scholar
- Yulong Gu, Zhuoye Ding, Shuaiqiang Wang, Lixin Zou, Yiding Liu, and Dawei Yin. 2020. Deep Multifaceted Transformers for Multi-objective Ranking in Large-Scale E-commerce Recommender Systems. In CIKM. ACM, 2493--2500.Google Scholar
- Huifeng Guo, Ruiming Tang, Yunming Ye, Zhenguo Li, and Xiuqiang He. 2017. DeepFM: A Factorization-Machine based Neural Network for CTR Prediction. In IJCAI.Google Scholar
- Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2015. Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. In ICCV. 1026--1034.Google Scholar
- Xinran He, Junfeng Pan, Ou Jin, Tianbing Xu, Bo Liu, Tao Xu, Yanxin Shi, Antoine Atallah, Ralf Herbrich, Stuart Bowers, and Joaquin Qui n onero Candela. 2014. Practical Lessons from Predicting Clicks on Ads at Facebook. In ADKDD. ACM.Google Scholar
- Tongwen Huang, Zhiqi Zhang, and Junlin Zhang. 2019. FiBiNET: combining feature importance and bilinear feature interaction for click-through rate prediction. In RecSys. ACM, 169--177.Google Scholar
- Manas R. Joglekar, Cong Li, Jay K. Adams, Pranav Khaitan, and Quoc V. Le. 2019. Neural Input Search for Large Scale Recommendation Models. CoRR, Vol. abs/1907.04471 (2019). arxiv: 1907.04471 http://arxiv.org/abs/1907.04471Google Scholar
- Yu-Chin Juan, Yong Zhuang, Wei-Sheng Chin, and Chih-Jen Lin. 2016. Field-aware Factorization Machines for CTR Prediction. In RecSys.Google Scholar
- Wang-Cheng Kang, Derek Zhiyuan Cheng, Tiansheng Yao, Xinyang Yi, Ting Chen, Lichan Hong, and Ed H. Chi. 2020. Deep Hash Embedding for Large-Vocab Categorical Feature Representations. CoRR, Vol. abs/2010.10784 (2020).Google Scholar
- Guolin Ke, Zhenhui Xu, Jia Zhang, Jiang Bian, and Tie-Yan Liu. 2019. DeepGBM: A Deep Learning Framework Distilled by GBDT for Online Prediction Tasks. In SIGKDD. ACM, 384--394.Google Scholar
- Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014).Google Scholar
- Jianxun Lian, Xiaohuan Zhou, Fuzheng Zhang, Zhongxia Chen, Xing Xie, and Guangzhong Sun. 2018. xDeepFM: Combining Explicit and Implicit Feature Interactions for Recommender Systems. In SIGKDD.Google Scholar
- Bin Liu, Ruiming Tang, Yingzhi Chen, Jinkai Yu, Huifeng Guo, and Yuzhou Zhang. 2019. Feature Generation by Convolutional Neural Network for Click-Through Rate Prediction. In WWW.Google Scholar
- Bin Liu, Niannan Xue, Huifeng Guo, Ruiming Tang, Stefanos Zafeiriou, Xiuqiang He, and Zhenguo Li. 2020 a. AutoGroup: Automatic Feature Grouping for Modelling Explicit High-Order Feature Interactions in CTR Prediction. In SIGIR. ACM.Google Scholar
- Bin Liu, Chenxu Zhu, Guilin Li, Weinan Zhang, Jincai Lai, Ruiming Tang, Xiuqiang He, Zhenguo Li, and Yong Yu. 2020 b. AutoFIS: Automatic Feature Interaction Selection in Factorization Models for Click-Through Rate Prediction. In SIGKDD.Google Scholar
- H Brendan McMahan, Gary Holt, David Sculley, Michael Young, Dietmar Ebner, Julian Grady, Lan Nie, Todd Phillips, Eugene Davydov, Daniel Golovin, et al. 2013. Ad click prediction: a view from the trenches. In SIGKDD. ACM, 1222--1230.Google Scholar
- Maxim Naumov, Dheevatsa Mudigere, Hao-Jun Michael Shi, Jianyu Huang, Narayanan Sundaraman, Jongsoo Park, Xiaodong Wang, Udit Gupta, Carole-Jean Wu, Alisson G. Azzolini, Dmytro Dzhulgakov, Andrey Mallevich, Ilia Cherniavskii, Yinghai Lu, Raghuraman Krishnamoorthi, Ansha Yu, Volodymyr Kondratenko, Stephanie Pereira, Xianjie Chen, Wenlin Chen, Vijay Rao, Bill Jia, Liang Xiong, and Misha Smelyanskiy. 2019. Deep Learning Recommendation Model for Personalization and Recommendation Systems. CoRR, Vol. abs/1906.00091 (2019).Google Scholar
- Jiarui Qin, Weinan Zhang, Xin Wu, Jiarui Jin, Yuchen Fang, and Yong Yu. 2020. User Behavior Retrieval for Click-Through Rate Prediction. In SIGIR. ACM.Google Scholar
- Yanru Qu, Han Cai, Kan Ren, Weinan Zhang, Yong Yu, Ying Wen, and Jun Wang. 2016. Product-based neural networks for user response prediction. In ICDM. IEEE, 1149--1154.Google Scholar
- Yanru Qu, Bohui Fang, Weinan Zhang, Ruiming Tang, Minzhe Niu, Huifeng Guo, Yong Yu, and Xiuqiang He. 2019. Product-based Neural Networks for User Response Prediction over Multi-field Categorical Data. ACM Trans. Inf. Syst., Vol. 37, 1 (2019), 5:1--5:35.Google ScholarDigital Library
- Steffen Rendle. 2010. Factorization Machines. In Proc. IEEE Int. Conf. Data Mining.Google Scholar
- Weiping Song, Chence Shi, Zhiping Xiao, Zhijian Duan, Yewen Xu, Ming Zhang, and Jian Tang. 2019. Autoint: Automatic feature interaction learning via self-attentive neural networks. In CIKM. 1161--1170.Google ScholarDigital Library
- Laurens Van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. Journal of machine learning research, Vol. 9, 11 (2008).Google Scholar
- Ruoxi Wang, Bin Fu, Gang Fu, and Mingliang Wang. 2017. Deep & Cross Network for Ad Click Predictions. In ADKDD. ACM, 12:1--12:7.Google Scholar
- Yichao Wang, Huifeng Guo, Ruiming Tang, Zhirong Liu, and Xiuqiang He. 2020. A Practical Incremental Method to Train Deep CTR Models. CoRR, Vol. abs/2009.02147 (2020).Google Scholar
- Weinan Zhang, Tianming Du, and Jun Wang. 2016. Deep learning over multi-field categorical data. In ECIR. Springer, 45--57.Google Scholar
- Xiangyu Zhao, Chong Wang, Ming Chen, Xudong Zheng, Xiaobing Liu, and Jiliang Tang. 2020. AutoEmb: Automated Embedding Dimensionality Search in Streaming Recommendations. arXiv preprint arXiv:2002.11252 (2020).Google Scholar
- Guorui Zhou, Na Mou, Ying Fan, Qi Pi, Weijie Bian, Chang Zhou, Xiaoqiang Zhu, and Kun Gai. 2019. Deep Interest Evolution Network for Click-Through Rate Prediction. In AAAI. 5941--5948.Google Scholar
- Guorui Zhou, Xiaoqiang Zhu, Chengru Song, Ying Fan, Han Zhu, Xiao Ma, Yanghui Yan, Junqi Jin, Han Li, and Kun Gai. 2018. Deep Interest Network for Click-Through Rate Prediction. In SIGKDD. 1059--1068.Google Scholar
Index Terms
- An Embedding Learning Framework for Numerical Features in CTR Prediction
Recommendations
Numerical Feature Representation with Hybrid N-ary Encoding
CIKM '22: Proceedings of the 31st ACM International Conference on Information & Knowledge ManagementNumerical features (e.g., statistical features) are widely used in recommender systems and online advertising. Existing approaches for numerical feature representation in industry are primarily based on discretization. However, hard-discretization based ...
Revisiting Cold-Start Problem in CTR Prediction: Augmenting Embedding via GAN
CIKM '22: Proceedings of the 31st ACM International Conference on Information & Knowledge ManagementClick-through rate (CTR) prediction is one of the core tasks in industrial applications such as online advertising and recommender systems. However, the performance of existing CTR models is hampered by the cold-start users who have very few historical ...
JointCTR: a joint CTR prediction framework combining feature interaction and sequential behavior learning
AbstractClick-through rate (CTR) is a positive feedback of user preferences or product purchases, and its small increase can bring huge benefits. Therefore, CTR prediction plays a key role in computing advertising and recommendation systems. Research ...
Comments