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

Wu, Chuhan; Wu, Fangzhao; Lyu, Lingjuan; Huang, Yongfeng; Xie, Xing

doi:10.1145/3506715

Cited by 22 publications

(15 citation statements)

References 39 publications

(59 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Yang et al [40] further proposed an improved version of vertical federated logistic regression that is free from the additional coordinator server. Wu et al [33] proposed a federated ad CTR prediction approach that can exploit user behavior data on multiple platforms in a privacypreserving way to empower both model training and inference. Zhang et al [45] proposed an efficient bi-level VFL method that supports asynchronous model updates on all platforms.…”

Section: Related Workmentioning

confidence: 99%

“…The target tasks on the three platforms are education prediction (16-way classification, platform 1), gender prediction (binary classification, platform 2), and income prediction (binary classification, platform 3) 11 . The second dataset is the Ad CTR prediction dataset used in [33]. We denote this dataset as CTR.…”

Section: Datasets and Experimental Settingsmentioning

confidence: 99%

“…We denote this dataset as CTR. Following the settings in [33], we assume that different types of user behaviors in this dataset, including historical clicked Ads, search queries, and browsed webpages, are kept by three different platforms (clicked Ads on platform 1, search queries on platform 2, and browsed webpages on platform 3). The target task on each platform is to predict whether a candidate Ad will be clicked by a target user based on his/her behaviors.…”

Section: Datasets and Experimental Settingsmentioning

confidence: 99%

“…The number of independent experiments for performance estimation is 5. We use logistic regression on Adult and FedCTR [33] on CTR as the backbone models. For the logistic regression algorithm, we use the default settings in Sklearn.…”

Section: Datasets and Experimental Settingsmentioning

confidence: 99%

See 3 more Smart Citations

Game of Privacy: Towards Better Federated Platform Collaboration under Privacy Restriction

Wu¹,

Wu²,

Qi³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Vertical federated learning (VFL) aims to train models from crosssilo data with different feature spaces stored on different platforms. Existing VFL methods usually assume all data on each platform can be used for model training. However, due to the intrinsic privacy risks of federated learning, the total amount of involved data may be constrained. In addition, existing VFL studies usually assume only one platform has task labels and can benefit from the collaboration, making it difficult to attract other platforms to join in the collaborative learning. In this paper, we study the platform collaboration problem in VFL under privacy constraints. We propose to incent different platforms through a reciprocal collaboration, where all platforms can exploit multi-platform information in the VFL framework to benefit their own tasks. With limited privacy budgets, each platform needs to wisely allocate its data quotas for collaboration with other platforms. Thereby, they naturally form a multi-party game. There are two core problems in this game, i.e., how to appraise other platforms' data value to compute game rewards and how to optimize policies to solve the game. To evaluate the contributions of other platforms' data, each platform offers a small amount of "deposit" data to participate in the VFL. We propose a performance estimation method to predict the expected model performance when involving different amount combinations of inter-platform data. To solve the game, we propose a platform negotiation method that simulates the bargaining among platforms and locally optimizes their policies via gradient descent. Extensive experiments on two real-world datasets show that our approach can effectively facilitate the collaborative exploitation of multi-platform data in VFL under privacy restrictions.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Datasets and Experimental Settingsmentioning

confidence: 99%

Section: Datasets and Experimental Settingsmentioning

confidence: 99%

Section: Datasets and Experimental Settingsmentioning

confidence: 99%

See 2 more Smart Citations

Game of Privacy: Towards Better Federated Platform Collaboration under Privacy Restriction

Wu¹,

Wu²,

Qi³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Federated learning [23] is a machine learning technique that trains an algorithm across multiple decentralized edge devices (crossdevice) [13,25,45] or servers holding local data samples (crosssilo) [5,38,42], without exchanging them. Conventional federated learning protocol typically adopts FedAvg [23] to aggregate local parameters as follows:…”

Section: Background and Related Workmentioning

confidence: 99%

No One Left Behind: Inclusive Federated Learning over Heterogeneous Devices

Liu,

Wu,

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Federated learning (FL) is an important paradigm for training global models from decentralized data in a privacy-preserving way. Existing FL methods usually assume the global model can be trained on any participating client. However, in real applications, the devices of clients are usually heterogeneous, and have different computing power. Although big models like BERT have achieved huge success in AI, it is difficult to apply them to heterogeneous FL with weak clients. The straightforward solutions like removing the weak clients or using a small model to fit all clients will lead to some problems, such as under-representation of dropped clients and inferior accuracy due to data loss or limited model representation ability. In this work, we propose InclusiveFL, a client-inclusive federated learning method to handle this problem. The core idea of InclusiveFL is to assign models of different sizes to clients with different computing capabilities, bigger models for powerful clients and smaller ones for weak clients. We also propose an effective method to share the knowledge among multiple local models with different sizes. In this way, all the clients can participate in the model learning in FL, and the final model can be big and powerful enough. Besides, we propose a momentum knowledge distillation method to better transfer knowledge in big models on powerful clients to the small models on weak clients. Extensive experiments on many real-world benchmark datasets demonstrate the effectiveness of the proposed method in learning accurate models from clients with heterogeneous devices under the FL framework.

show abstract

K-PropNet: Knowledge-Enhanced Hybrid Heterogeneous Homogeneous Propagation Network for Recommender System

Li,

Ye,

et al. 2024

Web and Big Data

View full text Add to dashboard Cite

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

Cited by 22 publications

References 39 publications

Game of Privacy: Towards Better Federated Platform Collaboration under Privacy Restriction

Game of Privacy: Towards Better Federated Platform Collaboration under Privacy Restriction

No One Left Behind: Inclusive Federated Learning over Heterogeneous Devices

K-PropNet: Knowledge-Enhanced Hybrid Heterogeneous Homogeneous Propagation Network for Recommender System

Contact Info

Product

Resources

About