Title Of the Talk: Fairness in recommendation and matching systems
Speaker: Dr. Abhijnan Chakraborty
Host Faculty: Dr. Maunendra Desarkar
Date & Time:Thursday, 9th Jan 2020 & 2:30 PM - 3:30 PM
Venue: A-220
Abstract:
Algorithmic (data-driven) decision making is increasingly being used to assist or replace human decision making in domains with
high societal impact, such as banking (estimating creditworthiness), recruiting (ranking applicants), judiciary (offender
profiling) and journalism (recommending news-stories). Consequently, in recent times, multiple research works have attempted
to identify (measure) bias or unfairness in algorithmic decisions and proposed mechanisms to control (mitigate) such biases.
However, the emphasis of existing works has been on fairness in supervised classification or regression tasks, and fairness
issues in other scenarios remain relatively unexplored. In this talk, I’ll cover our recent works on fairness in recommendation
and matching systems, where the algorithms need to fairly consider the preferences of multiple sides. I’ll introduce the notions
of fairness in these contexts and propose techniques to achieve them. Additionally, I’ll briefly touch upon the possibility of
utilizing user interface of platforms (choice architecture) to achieve fair outcomes in certain scenarios. I’ll conclude the talk
with a list of open questions and directions for future work
Speaker Profile:
Abhijnan Chakraborty is a Post-doctoral Researcher at the Max Planck Institute for Software Systems (MPI-SWS), Germany. He
obtained his PhD from the Indian Institute of Technology (IIT) Kharagpur under the supervision of Prof. Niloy Ganguly (IIT
Kharagpur) and Prof. Krishna Gummadi (MPI-SWS). During PhD, he was awarded the Google India PhD Fellowship and the Prime
Minister's Fellowship for Doctoral Research. Prior to joining PhD, he spent two years at Microsoft Research India, working
in the area of mobile systems. His current research interests span the broad area of Computing and Society, covering the
research domains of Social Computing, Information Retrieval and Fairness in Machine Learning. He has authored several papers
in top-tier computer science conferences including WWW, KDD, AAAI, CSCW, ICWSM and MobiCom. His research works have won the
best paper award at ASONAM'16 and best poster award at ECIR’19. He is one of the recipients of the highly competitive research
grants from the Data Transparency Lab to advance his research on fairness and transparency in algorithmic systems. More details
about him can be found at
Speaker Profile page
Dates:
Thursday, 9th Jan 2020 & 2:30 PM - 3:30 PM