Neural CTR Prediction for Native Ad

An, Mingxiao; Wu, Fangzhao; Wang, Heyuan; Di, Tao; Huang, Jianqiang; Xie, Xing

doi:10.1007/978-3-030-32381-3_48

Cited by 6 publications

(24 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, from her webpage browsing behaviors we can infer that this user may be interested in cars since she browsed a webpage with title ł2021 Chevrolet Carsž, and it is appropriate to display the native ad łSee the latest new models from Chevroletž to her. Thus, incorporating user behaviors on multiple platforms is useful for modeling user interest more accurately and can beneit native ad CTR prediction, which has been validated by existing studies [1]. For example, An et al [1] found that combining users' searching behaviors and webpage browsing behaviors can achieve better performance on native ad CTR prediction than using single kind of user behaviors.…”

Section: Introductionmentioning

confidence: 90%

“…Thus, incorporating user behaviors on multiple platforms is useful for modeling user interest more accurately and can beneit native ad CTR prediction, which has been validated by existing studies [1]. For example, An et al [1] found that combining users' searching behaviors and webpage browsing behaviors can achieve better performance on native ad CTR prediction than using single kind of user behaviors. However, online user behaviors such as the queries they searched and the webpages they browsed are highly privacy-sensitive.…”

Section: Introductionmentioning

confidence: 90%

“…These deep learning based CTR prediction methods for display ads on e-commerce platform usually rely on the user behaviors on the same platform to model user interest. However, besides the e-commerce platform, native ads are widely displayed on many other online platforms such as news websites [1]. The user behaviors on these platforms may have insuicient clues to infer user interest in ads.…”

Section: Related Work 21 Ctr Predictionmentioning

confidence: 99%

“…Thus, these CTR prediction methods designed for display ads on e-commerce platform may be not optimal for native ads. There are only a few studies for native ad CTR prediction [1,29]. For example, An et al [1] proposed to model user interest for native ad CTR prediction from their search queries and browsed webpages.…”

Section: Related Work 21 Ctr Predictionmentioning

confidence: 99%

“…Although the CTR prediction for search ads and display ads has been widely studied [17,44], the research on native ads is very limited [1]. Compared with search ads which are displayed based on users' intents inferred from their search queries, there is no explicit user intent for native ads, making it more diicult to predict the click probability.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

FedCTR: Federated Native Ad CTR Prediction with Cross-platform User Behavior Data

Lyu³

et al. 2022

ACM Trans. Intell. Syst. Technol.

Self Cite

View full text Add to dashboard Cite

Native ad is a popular type of online advertisement which has similar forms with the native content displayed on websites. Native ad click-through rate (CTR) prediction is useful for improving user experience and platform revenue. However, it is challenging due to the lack of explicit user intent, and user behaviors on the platform with native ads may be insufficient to infer users’ interest in ads. Fortunately, user behaviors exist on many online platforms which can provide complementary information for user interest mining. Thus, leveraging multi-platform user behaviors is useful for native ad CTR prediction. However, user behaviors are highly privacy-sensitive, and the behavior data on different platforms cannot be directly aggregated due to user privacy concerns and data protection regulations. Existing CTR prediction methods usually require centralized storage of user behavior data for user modeling, which cannot be directly applied to the CTR prediction task with multi-platform user behaviors. In this paper, we propose a federated native ad CTR prediction method named FedCTR, which can learn user interest representations from cross-platform user behaviors in a privacy-preserving way. On each platform a local user model learns user embeddings from the local user behaviors on that platform. The local user embeddings from different platforms are uploaded to a server for aggregation, and the aggregated ones are sent to the ad platform for CTR prediction. Besides, we apply local differential privacy (LDP) and differential privacy (DP) to the local and aggregated user embeddings respectively for better privacy protection. Moreover, we propose a federated framework for collaborative model training with distributed models and user behaviors. Extensive experiments on real-world dataset show that FedCTR can effectively leverage multi-platform user behaviors for native ad CTR prediction in a privacy-preserving manner.

show abstract

Section: Introductionmentioning

confidence: 90%

Section: Introductionmentioning

confidence: 90%

Section: Related Work 21 Ctr Predictionmentioning

confidence: 99%

Section: Related Work 21 Ctr Predictionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

FedCTR: Federated Native Ad CTR Prediction with Cross-platform User Behavior Data

Lyu³

et al. 2022

ACM Trans. Intell. Syst. Technol.

Self Cite

View full text Add to dashboard Cite

show abstract

PTUM: Pre-training User Model from Unlabeled User Behaviors via Self-supervision

Wu¹,

Wu²,

Qi³

et al. 2020

Findings of the Association for Computational Linguistics: EMNLP 2020

Self Cite

View full text Add to dashboard Cite

User modeling is critical for many personalized web services. Many existing methods model users based on their behaviors and the labeled data of target tasks. However, these methods cannot exploit useful information in unlabeled user behavior data, and their performance may be not optimal when labeled data is scarce. Motivated by pre-trained language models which are pre-trained on large-scale unlabeled corpus to empower many downstream tasks, in this paper we propose to pretrain user models from large-scale unlabeled user behaviors data. We propose two selfsupervision tasks for user model pre-training. The first one is masked behavior prediction, which can model the relatedness between historical behaviors. The second one is next K behavior prediction, which can model the relatedness between past and future behaviors. The pre-trained user models are finetuned in downstream tasks to learn task-specific user representations. Experimental results on two realworld datasets validate the effectiveness of our proposed user model pre-training method.

show abstract

FedCTR: Federated Native Ad CTR Prediction with Multi-Platform User Behavior Data

Wu¹,

Wu²,

Di³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Native ad is a popular type of online advertisement which has similar forms with the native content displayed on websites. Native ad CTR prediction is useful for improving user experience and platform revenue. However, it is a challenging task due to the lack of explicit user intent, and users' behaviors on the platform with native ads may not be sufficient to infer their interest in ads. Fortunately, user behaviors exist on many online platforms and they can provide complementary information for user interest mining. Thus, leveraging multi-platform user behaviors is useful for native ad CTR prediction. However, user behaviors are highly privacysensitive and the behavior data on different platforms cannot be directly aggregated due to user privacy concerns and data protection regulations like GDPR. Existing CTR prediction methods usually require centralized storage of user behavior data for user modeling and cannot be directly applied to the CTR prediction task with multi-platform user behaviors. In this paper, we propose a federated native ad CTR prediction method named FedCTR, which can learn user interest representations from their behaviors on multiple platforms in a privacy-preserving way without the need of centralized storage. On each platform a local user model is used to learn user embeddings from the local user behaviors on that platform. The local user embeddings from different platforms are uploaded to a server for aggregation, and the aggregated user embeddings are sent to the ad platform for CTR prediction. Besides, we apply local differential privacy (LDP) and differential privacy (DP) techniques to the local and aggregated user embeddings respectively for better privacy protection. Moreover, we propose a federated framework for collaborative model training with distributed models and distributed user behaviors. Extensive experiments on real-world dataset demonstrate that the proposed method can effectively leverage multi-platform user behaviors for native ad CTR prediction in a privacy-preserving manner.

show abstract

Neural CTR Prediction for Native Ad

Cited by 6 publications

References 17 publications

FedCTR: Federated Native Ad CTR Prediction with Cross-platform User Behavior Data

FedCTR: Federated Native Ad CTR Prediction with Cross-platform User Behavior Data

PTUM: Pre-training User Model from Unlabeled User Behaviors via Self-supervision

FedCTR: Federated Native Ad CTR Prediction with Multi-Platform User Behavior Data

Contact Info

Product

Resources

About