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

Abstract

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.

Data Cooperatives as a Catalyst for Collaboration, Data Sharing and the Digital Transformation of the Construction Sector

“…Here, a federator ensures sovereign data exchange between data providers and consumers. The term "federated" means that balanced and fair regulation ensures that the various stakeholders as a whole benefit from the data exchange [17,18]. The prerequisite for data exchange in a multi-stakeholder environment is therefore not only based on technical implementation, but also on fair and transparent regulation that is implemented in a trustworthy manner via an institution authorized for this purpose, the "federator" [19].…”

Data Cooperatives as a Catalyst for Collaboration, Data Sharing and the Digital Transformation of the Construction Sector

“…A federator guarantees secure exchange of data between data providers and data consumers. The term "federated" means that balanced and fair regulation ensures that the various stakeholders as a whole benefit from the data exchange [17,18]. The prerequisite for data exchange in a Figure 1.…”

“…A federator guarantees secure exchange of data between data providers and data consumers. The term "federated" means that balanced and fair regulation ensures that the various stakeholders as a whole benefit from the data exchange [17,18]. The prerequisite for data exchange in a multi-stakeholder environment is therefore not only based on technical implementation, but also on fair and transparent regulation that is implemented in a trustworthy manner via an institution authorized for this purpose, the "federator" [19].…”