{"type":"ScholarlyArticle","title":"Disguise Adversarial Networks for Click-through Rate Prediction","authors":[{"name":"Yue Deng","slug":"yue-deng","given":"Yue","family":"Deng","affiliation":"Samsung Research America , Mountain View , CA , USA"},{"name":"Yilin Shen","slug":"yilin-shen","given":"Yilin","family":"Shen","affiliation":"Samsung Research America , Mountain View , CA , USA"},{"name":"Hongxia Jin","slug":"hongxia-jin","given":"Hongxia","family":"Jin","affiliation":"Samsung Research America , Mountain View , CA , USA"}],"abstract":"We introduced an  adversarial learning framework for improving CTR prediction in Ads recommendation. Our approach was motivated by observing the extremely low click-through rate and imbalanced label distribution in the historical Ads impressions.  We hence proposed a Disguise-Adversarial-Networks (DAN) to  improve the accuracy of supervised learning with limited positive-class information. In the context of CTR prediction, the rationality behind DAN could be intuitively understood as ``non-clicked Ads makeup''. DAN disguises the disliked Ads impressions (non-clicks) to be interesting ones and encourages a discriminator to classify these disguised Ads as positive recommendations. In an adversarial aspect, the discriminator should be sober-minded which is optimized to allocate these disguised Ads to their inherent classes according to an unsupervised information theoretic assignment strategy. We applied DAN to two Ads datasets including both mobile and display Ads for CTR prediction. The results showed that our DAN approach significantly outperformed other supervised learning and generative adversarial networks (GAN) in CTR prediction.","doi":"10.24963/ijcai.2017/220","url":"https://ijcai.org/proceedings/2017/220","pdf":"https://ijcai.org/proceedings/2017/0220.pdf","markdown":"https://ijcai.org/proceedings/2017/220.md","bibtex":"https://ijcai.org/proceedings/2017/bibtex/220","volume":{"slug":"2017","title":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2017","url":"https://ijcai.org/proceedings/2017/","year":2017,"location":"Melbourne, Australia","dates":"19-25 August 2017","editors":"Carles Sierra","isbn":"978-0-9992411-0-3","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2017"},"section":"Machine Learning A-R","track":"Main track","number":220,"pages":{"first":1589,"last":1595},"keywords":["Machine Learning: Neural Networks","Machine Learning: Classification","Machine Learning: Learning Preferences or Rankings","Machine Learning: Deep Learning"],"videos":[],"references":[{"position":1,"raw":"[Ava, 2015] Avazu mobile ads ctr dataset. https://www.kaggle.com/c/avazu-ctr-prediction/data, 2015.","title":"Avazu mobile ads ctr dataset","authors":"Ava","year":"2015","venue":null,"doi":null,"url":"https://www.kaggle.com/c/avazu-ctr-prediction/data,2015","internal_url":null},{"position":2,"raw":"[Bao et al., 2017a] Feng Bao, Yue Deng, Mulong Du, Zhi- quan Ren, Qingzhao Zhang, Yanyu Zhao, Jinli Suo, Zhengdong Zhang, Meilin Wang, and Qionghai Dai. Prob- abilistic natural mapping of gene-level tests for genome- wide association studies. Brief Bioinform, (bbx002), 2017.","title":"Probabilistic natural mapping of gene-level tests for genomewide association studies","authors":"Bao","year":"2017","venue":"Brief Bioinform","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Bao et al., 2017b] Feng Bao, Yue Deng, Yanyu Zhao, Jinli Suo, and Qionghai Dai. Bosco: boosting corrections for genome-wide association studies with imbalanced sam- ples. IEEE Transactions on NanoBioscience, PP(99):1-1, 2017.","title":"Bosco: boosting corrections for genome-wide association studies with imbalanced samples","authors":"Bao","year":"2017","venue":"IEEE Transactions on NanoBioscience","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Bard, 2013] Jonathan F Bard. Practical bilevel optimiza- tion: algorithms and applications, volume 30. Springer Science & Business Media, 2013.","title":"Practical bilevel optimization: algorithms and applications","authors":"Jonathan F Bard","year":"2013","venue":null,"doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Chawla et al., 2002] Nitesh V. Chawla, Kevin W. Bowyer, Lawrence O. Hall, and W. Philip Kegelmeyer. Smote: syn- thetic minority over-sampling technique. JAIR, 16:321- 357, 2002.","title":"Smote: synthetic minority over-sampling technique","authors":"V Nitesh, Kevin W Chawla, Lawrence O Bowyer, W Philip Hall, Kegelmeyer","year":"2002","venue":"JAIR","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Chen and Yan, 2012] Ye Chen and Tak W Yan. Position- normalized click prediction in search advertising. In ACM SIGKDD, pages 795-803. ACM, 2012.","title":"Positionnormalized click prediction in search advertising","authors":"Chen, Yan ; ] Ye Chen, Tak W Yan","year":"2012","venue":"ACM SIGKDD","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Chen et al., 2016] Xi Chen, Yan Duan, Rein Houthooft, John Schulman, Ilya Sutskever, and Pieter Abbeel. Info- gan: Interpretable representation learning by information maximizing generative adversarial nets. In Nips, pages 2172-2180, 2016. [Cri, 2015] Criteo display ads ctr dataset. https://www.kaggle.com/c/criteo-display-ad-challenge, 2015.","title":"Infogan: Interpretable representation learning by information maximizing generative adversarial nets","authors":"Xi Chen, Yan Duan, Rein Houthooft, John Schulman, Ilya Sutskever, Pieter Abbeel","year":"2015","venue":"Criteo display ads ctr dataset","doi":null,"url":"https://www.kaggle.com/c/criteo-display-ad-challenge,2015","internal_url":null},{"position":8,"raw":"[Deng et al., 2013] Yue Deng, Qionghai Dai, Risheng Liu, Zengke Zhang, and Sanqing Hu. Low-rank structure learning via nonconvex heuristic recovery. IEEE TNNLS, 24(3):383-396, March 2013.","title":"Low-rank structure learning via nonconvex heuristic recovery","authors":"Yue Deng, Qionghai Dai, Risheng Liu, Zengke Zhang, Sanqing Hu","year":"2013","venue":"IEEE TNNLS","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Deng et al., 2016a] Yue Deng, Feng Bao, Xuesong Deng, Ruiping Wang, Youyong Kong, and Qionghai Dai. Deep and structured robust information theoretic learning for image analysis. IEEE TIP, 25(9):4209-4221, Sept 2016.","title":"Deep and structured robust information theoretic learning for image analysis","authors":"Deng","year":"2016","venue":"IEEE TIP","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Deng et al., 2016b] Yue Deng, Zhiquan Ren, Youyong Kong, Feng Bao, and Qionghai Dai. A hierarchical fused fuzzy deep neural network for data classification. IEEE TFS, 2016.","title":"A hierarchical fused fuzzy deep neural network for data classification","authors":"Deng","year":"2016","venue":"IEEE TFS","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Deng et al., 2017a] Yue Deng, Feng Bao, Youyong Kong, Zhiquan Ren, and Qionghai Dai. Deep direct reinforce- ment learning for financial signal representation and trad- ing. IEEE TNNLS, 28(3):653-664, March 2017.","title":"Deep direct reinforcement learning for financial signal representation and trading","authors":"Deng","year":"2017","venue":"IEEE TNNLS","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Deng et al., 2017b] Yue Deng, Yanyu Zhao, Zhiquan Ren, Youyong Kong, Feng Bao, and Qionghao Dai. Discrimi- nant kernel assignment for image coding. IEEE Transac- tions on Cybernetics, 47(6):1434-1445, June 2017.","title":"Discriminant kernel assignment for image coding","authors":"Deng","year":"2017","venue":"IEEE Transactions on Cybernetics","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Denton et al., 2015] Emily L Denton, Soumith Chintala, Rob Fergus, et al. Deep generative image models using a laplacian pyramid of adversarial networks. In Nips, pages 1486-1494, 2015.","title":"Deep generative image models using a laplacian pyramid of adversarial networks","authors":"Soumith Emily L Denton, Rob Chintala, Fergus","year":"2015","venue":"Nips","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Ganganwar, 2012] Vaishali Ganganwar. An overview of classification algorithms for imbalanced datasets. Inter- national Journal of Emerging Technology and Advanced Engineering, 2(4):42-47, 2012.","title":"An overview of classification algorithms for imbalanced datasets","authors":"Vaishali Ganganwar","year":"2012","venue":"International Journal of Emerging Technology and Advanced Engineering","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Gauthier, 2014] Jon Gauthier. Conditional generative adver- sarial nets for convolutional face generation. Technical Re- port, 2014:5, 2014.","title":"Conditional generative adversarial nets for convolutional face generation","authors":"Jon Gauthier, Gauthier","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Goodfellow et al., 2014] Ian Goodfellow, Jean Pouget- Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. Gen- erative adversarial nets. In Nips, pages 2672-2680, 2014.","title":"Generative adversarial nets","authors":"Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, Yoshua Bengio","year":"2014","venue":"Nips","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Han et al., 2005] Hui Han, Wen-Yuan Wang, and Bing- Huan Mao. Borderline-smote: a new over-sampling method in imbalanced data sets learning. In Interna- tional Conference on Intelligent Computing, pages 878- 887. Springer, 2005.","title":"Borderline-smote: a new over-sampling method in imbalanced data sets learning","authors":"Hui Han, Wen-Yuan Wang, Bing-Huan Mao","year":"2005","venue":"International Conference on Intelligent Computing","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[He et al., 2008] Haibo He, Yang Bai, Edwardo A Garcia, and Shutao Li. Adasyn: Adaptive synthetic sampling ap- proach for imbalanced learning. In IJCNN, pages 1322- 1328. IEEE, 2008.","title":"Adasyn: Adaptive synthetic sampling approach for imbalanced learning","authors":"Haibo He, Yang Bai, Edwardo A Garcia, Shutao Li","year":"2008","venue":"IJCNN","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Japkowicz, 2000] Nathalie Japkowicz. Learning from im- balanced data sets: a comparison of various strategies. In AAAI workshop on learning from imbalanced data sets, volume 68, pages 10-15.","title":"Learning from imbalanced data sets: a comparison of various strategies","authors":"Nathalie Japkowicz","year":null,"venue":"AAAI workshop on learning from imbalanced data sets","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[König et al., 2009] Arnd Christian König, Michael Gamon, and Qiang Wu. Click-through prediction for news queries. In SIGIR, pages 347-354. ACM, 2009.","title":"Click-through prediction for news queries","authors":"Arnd Christian König, Michael Gamon, Qiang Wu","year":"2009","venue":"SIGIR","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Krause et al., 2010] Andreas Krause, Pietro Perona, and Ryan G Gomes. Discriminative clustering by regularized information maximization. In Nips, pages 775-783, 2010.","title":"Discriminative clustering by regularized information maximization","authors":"Andreas Krause, Pietro Perona, Ryan G Gomes","year":"2010","venue":"Nips","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Li et al., 2010] Lihong Li, Wei Chu, John Langford, and Robert E Schapire. A contextual-bandit approach to per- sonalized news article recommendation. In WWW, pages 661-670. ACM, 2010.","title":"A contextual-bandit approach to personalized news article recommendation","authors":"Lihong Li, Wei Chu, John Langford, Robert E Schapire","year":"2010","venue":"WWW","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Lillicrap et al., 2015] Timothy P Lillicrap, Jonathan J Hunt, Alexander Pritzel, Nicolas Heess, Tom Erez, Yuval Tassa, David Silver, and Daan Wierstra. Continuous con- trol with deep reinforcement learning. arXiv preprint arXiv:1509.02971, 2015.","title":"Continuous control with deep reinforcement learning","authors":"Jonathan J Timothy P Lillicrap, Alexander Hunt, Nicolas Pritzel, Tom Heess, Yuval Erez, David Tassa, Daan Silver, Wierstra","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Odena, 2016] Augustus Odena. Semi-supervised learning with generative adversarial networks. arXiv preprint arXiv:1606.01583, 2016.","title":"Augustus Odena. Semi-supervised learning with generative adversarial networks","authors":"Odena","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Radford et al., 2015] Alec Radford, Luke Metz, and Soumith Chintala. Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv preprint arXiv:1511.06434, 2015.","title":"Unsupervised representation learning with deep convolutional generative adversarial networks","authors":"Radford","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Ren et al., 2016] Zhiquan Ren, Yue Deng, and Qionghai Dai. Local visual feature fusion via maximum margin mul- timodal deep neural network. Neurocomputing, 175:427- 432, 2016.","title":"Local visual feature fusion via maximum margin multimodal deep neural network","authors":"Ren","year":"2016","venue":"Neurocomputing","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Richardson et al., 2007] Matthew Richardson, Ewa Domi- nowska, and Robert Ragno. Predicting clicks: estimating the click-through rate for new ads. In WWW, pages 521- 530. ACM, 2007.","title":"Predicting clicks: estimating the click-through rate for new ads","authors":"Matthew Richardson, Ewa Dominowska, Robert Ragno","year":"2007","venue":"WWW","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Shi and Sha, 2012] Yuan Shi and Fei Sha. Information- theoretical learning of discriminative clusters for unsuper- vised domain adaptation. arXiv preprint arXiv:1206.6438, 2012.","title":"Informationtheoretical learning of discriminative clusters for unsupervised domain adaptation","authors":"Yuan Shi, Fei Sha","year":"2012","venue":null,"doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Yan et al., 2014] Ling Yan, Wu-jun Li, Gui-Rong Xue, and Dingyi Han. Coupled group lasso for web-scale ctr pre- diction in display advertising. In ICML, pages 802-810, 2014.","title":"Coupled group lasso for web-scale ctr prediction in display advertising","authors":"Ling Yan, Wu-Jun, Gui-Rong Li, Dingyi Xue, Han","year":"2014","venue":"ICML","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}