Enabling SQL-based Training Data Debugging for Federated Learning

Understand

How can we debug a logistical regression model in a federated learning setting when seeing the model behave unexpectedly (e.g., the model rejects all high-income customers' loan applications)? The SQL-based training data debugging framework has proved effective to fix this kind of issue in a non-federated learning setting.

• Given an unexpected query result over model predictions, this framework automatically removes the label errors from training data such that the unexpected behavior disappears in the retrained model.
• In this paper, we enable this powerful framework for federated learning.
• The key challenge is how to develop a security protocol for federated debugging which is proved to be secure, efficient, and accurate.