[1910.11160] Stochastic Channel-Based Federated Learning for Medical Data Privacy Preserving
We introduced a neural pruning process to the model, which could accelerate the training process and saturating speed of performances with little sacrifice of the final performances.Differential privacy could be further conducted on our models to evaluate the privacy-preserving ability quantitatively.
Abstract: Artificial neural network has achieved unprecedented success in the medical
domain. This success depends on the availability of massive and representative
datasets. However, data collection is often prevented by privacy concerns and
people want to take control over their sensitive information during both
training and using processes. To address this problem, we propose a
privacy-preserving method for the distributed system, Stochastic Channel-Based
Federated Learning (SCBF), which enables the participants to train a
high-performance model cooperatively without sharing their inputs.
Specifically, we design, implement and evaluate a channel-based update
algorithm for the central server in a distributed system, which selects the
channels with regard to the most active features in a training loop and uploads
them as learned information from local datasets. A pruning process is applied
to the algorithm based on the validation set, which serves as a model
accelerator. In the experiment, our model presents better performances and
higher saturating speed than the Federated Averaging method which reveals all
the parameters of local models to the server when updating. We also demonstrate
that the saturating rate of performance could be promoted by introducing a
pruning process. And further improvement could be achieved by tuning the
pruning rate. Our experiment shows that 57% of the time is saved by the pruning
process with only a reduction of 0.0047 in AUCROC performance and a reduction
of 0.0068 in AUCPR.
‹Figure 1: SCBF Model (Material and Methods)Figure 2: Comparison of SCBF and FA with and without pruning. The left graph evaluate these methods by AUC-ROC, while the right one uses AUC-PR. The proposed method SCBF outperforms others by both indicators and SCBFwP method obtains the quickest saturating speed. (Result)›