Privacy of federated QR decomposition using additive secure multiparty computation
This addresses privacy concerns in federated learning for domains like healthcare or finance, but it is incremental as it adapts an existing algorithm to a specific context.
The paper tackles the problem of performing QR decomposition in cross-silo federated learning without leaking raw data, proposing a privacy-aware scheme based on the Gram-Schmidt algorithm and applying it to federated linear regression.
Federated learning (FL) is a privacy-aware data mining strategy keeping the private data on the owners' machine and thereby confidential. The clients compute local models and send them to an aggregator which computes a global model. In hybrid FL, the local parameters are additionally masked using secure aggregation, such that only the global aggregated statistics become available in clear text, not the client specific updates. Federated QR decomposition has not been studied extensively in the context of cross-silo federated learning. In this article, we investigate the suitability of three QR decomposition algorithms for cross-silo FL and suggest a privacy-aware QR decomposition scheme based on the Gram-Schmidt algorithm which does not blatantly leak raw data. We apply the algorithm to compute linear regression in a federated manner.