An End-To-End Machine Learning Pipeline That Ensures Fairness Policies

10/18/2017
by   Samiulla Shaikh, et al.
0

In consequential real-world applications, machine learning (ML) based systems are expected to provide fair and non-discriminatory decisions on candidates from groups defined by protected attributes such as gender and race. These expectations are set via policies or regulations governing data usage and decision criteria (sometimes explicitly calling out decisions by automated systems). Often, the data creator, the feature engineer, the author of the algorithm and the user of the results are different entities, making the task of ensuring fairness in an end-to-end ML pipeline challenging. Manually understanding the policies and ensuring fairness in opaque ML systems is time-consuming and error-prone, thus necessitating an end-to-end system that can: 1) understand policies written in natural language, 2) alert users to policy violations during data usage, and 3) log each activity performed using the data in an immutable storage so that policy compliance or violation can be proven later. We propose such a system to ensure that data owners and users are always in compliance with fairness policies.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/12/2022

Long Term Fairness for Minority Groups via Performative Distributionally Robust Optimization

Fairness researchers in machine learning (ML) have coalesced around seve...
research
09/10/2022

Code Compliance Assessment as a Learning Problem

Manual code reviews and static code analyzers are the traditional mechan...
research
08/31/2022

End-to-End Rationale Reconstruction

The logic behind design decisions, called design rationale, is very valu...
research
07/20/2020

Crowd, Lending, Machine, and Bias

Big data and machine learning (ML) algorithms are key drivers of many fi...
research
02/09/2019

PoliFi: Airtime Policy Enforcement for WiFi

As WiFi grows ever more popular, airtime contention becomes an increasin...
research
06/09/2021

Geospatial Reasoning with Shapefiles for Supporting Policy Decisions

Policies are authoritative assets that are present in multiple domains t...
research
10/03/2021

Dr.Aid: Supporting Data-governance Rule Compliance for Decentralized Collaboration in an Automated Way

Collaboration across institutional boundaries is widespread and increasi...

Please sign up or login with your details

Forgot password? Click here to reset