Timezone: »

 
Poster
Sample Selection for Fair and Robust Training
Yuji Roh · Kangwook Lee · Steven Whang · Changho Suh

Thu Dec 09 04:30 PM -- 06:00 PM (PST) @
in Poster Session 7 »

Fairness and robustness are critical elements of Trustworthy AI that need to be addressed together. Fairness is about learning an unbiased model while robustness is about learning from corrupted data, and it is known that addressing only one of them may have an adverse affect on the other. In this work, we propose a sample selection-based algorithm for fair and robust training. To this end, we formulate a combinatorial optimization problem for the unbiased selection of samples in the presence of data corruption. Observing that solving this optimization problem is strongly NP-hard, we propose a greedy algorithm that is efficient and effective in practice. Experiments show that our method obtains fairness and robustness that are better than or comparable to the state-of-the-art technique, both on synthetic and benchmark real datasets. Moreover, unlike other fair and robust training baselines, our algorithm can be used by only modifying the sampling step in batch selection without changing the training algorithm or leveraging additional clean data.

Keywords: Optimization · Robustness · Fairness

Author Information

Yuji Roh (KAIST)
Kangwook Lee (UW Madison)
Steven Whang (KAIST)
Changho Suh (KAIST)

Changho Suh is an Ewon Associate Professor in the School of Electrical Engineering at Korea Advanced Institute of Science and Technology (KAIST). He recevied the B.S. and M.S. degrees in Electrical Engineering from KAIST in 2000 and 2002 respectively, and the Ph.D. degree in Electrical Engineering and Computer Sciences from UC-Berkeley in 2011, under the supervision of Prof. David Tse. From 2011 to 2012, he was a postdoctoral associate at the Research Laboratory of Electronics in MIT. From 2002 to 2006, he had been with the Telecommunication R&D Center, Samsung Electronics. Dr. Suh received the 2015 IEIE Hadong Young Engineer Award, a 2015 Bell Labs Prize finalist, the 2013 IEEE Communications Society Stephen O. Rice Prize, the 2011 David J. Sakrison Memorial Prize (top research award in the UC-Berkeley EECS Department), and the 2009 IEEE ISIT Best Student Paper Award.

More from the Same Authors