公开(公告)号：US20250094862A1

公开(公告)日：2025-03-20

申请号：US18529182

申请日：2023-12-05

Applicant: Oracle International Corporation

Inventor： Yasha Pushak ,  Mathieu Godbout ,  Hesam Fathi Moghadam ,  Sungpack Hong ,  Hassan Chafi

IPC: G06N20/00

Abstract: In an embodiment, a computer generates a respective original inference from each of many records. Permuted values are selected for a feature from original values of the feature. Based on the permuted values for the feature, a permuted inference is generated from each record. Fairness and accuracy of the original and permuted inferences are measured. For each of many features, the computer measures a respective impact on fairness of a machine learning model, and a respective impact on accuracy of the machine learning model. A global explanation of the machine learning model is generated and presented based on, for multiple features, the impacts on fairness and accuracy. Based on the global explanation, an interactive indication to exclude or include a particular feature is received. The machine learning model is (re-)trained based on the interactive indication to exclude or include the particular feature, which may increase the fairness of the model.

公开(公告)号：US20240403674A1

公开(公告)日：2024-12-05

申请号：US18529300

申请日：2023-12-05

Applicant: Oracle International Corporation

Inventor： Mathieu Godbout ,  Yasha Pushak ,  Hesam Fathi Moghadam ,  Sungpack Hong ,  Hassan Chafi

IPC: G06N7/01 ,  G06N20/00

Abstract: In an embodiment, a computer infers, from an input (e.g. that represents a person) that contains a value of a sensitive feature that has a plurality of multipliers, a probability of a majority class (i.e. an outcome). Based on the value of the sensitive feature in the input, from the multipliers of the sensitive feature, a multiplier is selected that is specific to both of the sensitive feature and the value of the sensitive feature. The input is classified based on a multiplicative product of the probability of the majority class and the multiplier that is specific to both of the sensitive feature and the value of the sensitive feature. In an embodiment, a black-box bi-objective optimizer generates multipliers on a Pareto frontier from which a user may interactively select a combination of multipliers that provide a best tradeoff between fairness and accuracy.