公开(公告)号：US11593648B2

公开(公告)日：2023-02-28

申请号：US16844006

申请日：2020-04-09

Applicant: Adobe Inc.

Inventor： Sana Lee ,  Po Ming Law ,  Moumita Sinha ,  Fan Du

IPC: G06N3/08 ,  G06N20/00

Abstract: This disclosure involves detecting biases in predictive models and the root cause of those biases. For example, a processing device receives test data and training data from a client device. The processing device identifies feature groups from the training data and the test data generates performance metrics and baseline metrics for a feature group. The processing device detects biases through a comparison of the performance metrics and the baseline metrics the feature group. The processing device then isolates a portion of the training data that corresponds to the detected bias. The processing device generates a model correction usable to remove the bias from the predictive model.

公开(公告)号：US20210319333A1

公开(公告)日：2021-10-14

申请号：US16844006

申请日：2020-04-09

Applicant: Adobe Inc.

Inventor： Sana Lee ,  Po Ming Law ,  Moumita Sinha ,  Fan Du

IPC: G06N5/04 ,  G06N20/00

Abstract: This disclosure involves detecting biases in predictive models and the root cause of those biases. For example, a processing device receives test data and training data from a client device. The processing device identifies feature groups from the training data and the test data generates performance metrics and baseline metrics for a feature group. The processing device detects biases through a comparison of the performance metrics and the baseline metrics the feature group. The processing device then isolates a portion of the training data that corresponds to the detected bias. The processing device generates a model correction usable to remove the bias from the predictive model.