Adversarial Learning of Group and Individual Fair Representations

MPhil Thesis Defence


Title: "Adversarial Learning of Group and Individual Fair Representations"

By

Mr. Zheng ZHANG


Abstract

Fairness is increasingly becoming an important issue in machine learning. 
Representation learning is a popular approach recently that aims at 
mitigating discrimination by generating representation on the historical 
data so that further predictive analysis conducted on the representation 
is fair. Inspired by this approach, we propose a novel structure, called 
GIFair, for generating a representation that can simultaneously reconcile 
utility with fairness by adversarial learning. Compared with most relevant 
studies that only focus on group fairness without individual fairness, 
GIFair makes sure that the classifiers trained on the generated 
representation achieve both individual fairness and group fairness. A 
theoretical proof is provided to show that except in highly constrained 
special cases, group fairness and individual fairness cannot be satisfied 
simultaneously, so we need to make a trade-off between group fairness and 
individual fairness in addition to the utility of classifiers. Experiments 
conducted on two real datasets show that GIFair can achieve a better 
utility-fairness trade-off compared with existing models.


Date:  			Monday, 16 August 2021

Time:			4:00pm - 6:00pm

Zoom meeting: 
https://hkust.zoom.us/j/96598379164?pwd=R1Z2Nm5SR0NoVXA0aEFlU3NDRStydz09

Committee Members:	Prof. Raymond Wong (Supervisor)
 			Prof. Gary Chan (Supervisor)
 			Prof. Dit-Yan Yeung (Chairperson)
 			Dr. Wilfred Ng


**** ALL are Welcome ****