Max-Planck-Institut für Informatik
max planck institut
informatik
mpii logo Minerva of the Max Planck Society
 

MPI-INF or MPI-SWS or Local Campus Event Calendar

<< Previous Entry Next Entry >> New Event Entry Edit this Entry Login to DB (to update, delete)
What and Who
Title:Beyond Distributive Fairness in Algorithmic Decision Making: Feature Selection for Procedurally Fair Learning
Speaker:Nina Grgić-Hlača
coming from:Max Planck Institute for Software Systems
Speakers Bio:
Event Type:SWS Student Defense Talks - Qualifying Exam
Visibility:SWS
We use this to send out email in the morning.
Level:Expert Audience
Language:English
Date, Time and Location
Date:Friday, 10 November 2017
Time:15:00
Duration:60 Minutes
Location:Saarbrücken
Building:E1 5
Room:029
Abstract
With wide-spread usage of machine learning methods in numerous domains involving human subjects, several studies have raised questions about the potential for unfairness towards certain individuals or groups.

A number of recent works have proposed methods to measure and eliminate unfairness from machine learning methods. However, most of this work has focused on only one dimension of fair decision making: distributive fairness, i.e., the fairness of the decision outcomes. In this work, we leverage the rich literature on organizational justice and focus on another dimension of fair decision making: procedural fairness, i.e., the fairness of the decision making process.

We propose measures for procedural fairness that consider the input features used in the decision process, and evaluate the moral judgments of humans regarding the use of these features. We operationalize these measures on two real world datasets using human surveys on the Amazon Mechanical Turk (AMT) platform, demonstrating that we capture important properties of procedurally fair decision making. We provide fast submodular mechanisms to optimize the tradeoff between procedural fairness and prediction accuracy. On our datasets, we observe empirically that procedural fairness may be achieved with little cost to outcome fairness, but that some loss of accuracy is unavoidable.

Contact
Name(s):
Video Broadcast
Video Broadcast:NoTo Location:
Tags, Category, Keywords and additional notes
Note:
Attachments, File(s):

Created by:Maria-Louise Albrecht/MPI-KLSB, 11/03/2017 10:16 AMLast modified by:Maria-Louise Albrecht/MPI-KLSB, 11/03/2017 10:21 AM
  • Maria-Louise Albrecht, 11/03/2017 10:21 AM -- Created document.