Federated Visualization: A Privacy-preserving Strategy for Aggregated Visual Query
This addresses privacy concerns for users in decentralized data visualization, though it appears incremental as it applies an existing federated learning paradigm to a new domain.
The paper tackles the problem of preserving privacy in decentralized visualization by adapting the federated learning framework to create a federated visualization strategy, resulting in two implementations that were validated for effectiveness and robustness in real scenarios through expert review.
We present a novel privacy preservation strategy for decentralized visualization. The key idea is to imitate the flowchart of the federated learning framework, and reformulate the visualization process within a federated infrastructure. The federation of visualization is fulfilled by leveraging a shared global module that composes the encrypted externalizations of transformed visual features of data pieces in local modules. We design two implementations of federated visualization: a prediction-based scheme, and a query-based scheme. We demonstrate the effectiveness of our approach with a set of visual forms, and verify its robustness with evaluations. We report the value of federated visualization in real scenarios with an expert review.