Adaptive fairness improvement based causality analysis
Given a discriminating neural network, the problem of fairness improvement is to systematically reduce discrimination without significantly scarifies its performance (i.e., accuracy). Multiple categories of fairness improving methods have been proposed for neural networks, including pre-processing,...
Saved in:
Main Authors: | ZHANG, Mengdi, SUN, Jun |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2022
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/7280 https://ink.library.smu.edu.sg/context/sis_research/article/8283/viewcontent/2209.07190.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
Similar Items
-
TESTSGD: Interpretable testing of neural networks against subtle group discrimination
by: ZHANG, Mengdi, et al.
Published: (2023) -
Towards explainable neural network fairness
by: ZHANG, Mengdi
Published: (2024) -
A fair evaluation of the potential of machine learning in maritime transportation
by: Luo, Xi, et al.
Published: (2024) -
INTERPRETABILITY AND FAIRNESS IN MACHINE LEARNING: A FORMAL METHODS APPROACH
by: BISHWAMITTRA GHOSH
Published: (2023) -
SCALES: From Fairness Principles to Constrained Decision-Making
by: Balakrishnan, Sreejith, et al.
Published: (2022)