{"id":118388,"date":"2021-08-20T18:10:49","date_gmt":"2021-08-20T09:10:49","guid":{"rendered":"http:\/\/175.125.95.178\/ai-in-computer\/18388\/"},"modified":"2026-04-19T01:46:36","modified_gmt":"2026-04-18T16:46:36","slug":"18388","status":"publish","type":"ai-in-computer","link":"http:\/\/ee.presscat.kr\/en\/ai-in-computer\/18388\/","title":{"rendered":"Prof. Steven Euijong Whang and Prof. Changho Suh\u2019s Research Team Develops a New Batch Selection Technique for Fair AI"},"content":{"rendered":"

Professor. Steven Euijong Whang and Changho Suh\u2019s research team in the School of Electrical Engineering has developed a new batch selection technique for fair artificial intelligence (AI) systems. The research was led by Ph.D. student Yuji Roh (advisor: Steven Euijong Whang) and was conducted in collaboration with Professor Kangwook Lee from the Department of Electrical and Computer Engineering at the University of Wisconsin-Madison.<\/span><\/span><\/span><\/span><\/span><\/p>\n

 <\/p>\n

AI technologies are now widespread and influence everyday lives of humans. Unfortunately, researchers have recently observed that machine learning models may discriminate against specific demographics or individuals. As a result, there is a growing social consensus that AI systems need to be fair.<\/span><\/span><\/span><\/span><\/span><\/p>\n

 <\/p>\n

The research team proposes FairBatch, a new batch selection technique for building fair machine learning models. Existing fair training algorithms require significant non-trivial modifications either in the training data or model architecture. In contrast, FairBatch effectively achieves high accuracy and fairness with only a single-line change of code in the batch selection, which enables FairBatch to be easily deployed in various applications. FairBatch\u2019s key approach is solving a bi-level optimization for jointly achieving accuracy and fairness.<\/span><\/span><\/span><\/span><\/span><\/p>\n

 <\/p>\n

This research was presented at the International Conference for Learning Representations (ICLR) 2021, a top machine learning conference. <\/span><\/span>More details are in the links below. <\/span><\/span><\/span><\/span><\/span><\/p>\n

\"\"<\/div>\n<\/p>\n

Figure 1. A scenario that shows how FairBatch adaptively adjusts batch ratios in model training for fairness.<\/span><\/span><\/span><\/span><\/span><\/p>\n

 <\/p>\n

<\/p>\n

\"\"<\/div>\n

<\/span><\/span><\/span><\/span><\/span><\/p>\n

Figure 2.  PyTorch code for model training where FairBatch is used for batch selection. Only a single-line code change is required to replace an existing sampler with FairBatch, marked in blue.<\/span><\/span><\/span><\/span><\/span><\/p>\n

 <\/p>\n

 <\/p>\n

[Paper information and links]<\/span><\/b><\/span><\/span><\/span><\/p>\n

\nTitle: FairBatch: Batch Selection for Model Fairness<\/span><\/span><\/span><\/span><\/span><\/p>\n

Authors: Yuji Roh (KAIST EE), Kangwook Lee (Wisconsin-Madison Electrical & Computer Engineering), Steven Euijong Whang (KAIST EE), and Changho Suh (KAIST EE)<\/span><\/span><\/span><\/span><\/span><\/p>\n

 <\/p>\n

Paper: <\/span><\/span>https:\/\/openreview.net\/forum?id=YNnpaAKeCfx<\/a><\/span><\/span><\/a><\/span><\/span><\/span><\/span><\/p>\n

Source code: <\/span><\/span>https:\/\/github.com\/yuji-roh\/fairbatch<\/a><\/span><\/span><\/a><\/span><\/span><\/span><\/span><\/p>\n

Slides: <\/span><\/span>https:\/\/docs.google.com\/presentation\/d\/1IfaYovisZUYxyofhdrgTYzHGXIwixK9EyoAsoE1YX-w\/edit?usp=sharing<\/a><\/span><\/span><\/a><\/span><\/span><\/span><\/span><\/p>\n

 <\/p>\n

 <\/span><\/div>\n

 <\/p>\n","protected":false},"excerpt":{"rendered":"

603<\/p>\n","protected":false},"featured_media":126855,"template":"","class_list":["post-118388","ai-in-computer","type-ai-in-computer","status-publish","has-post-thumbnail","hentry"],"acf":[],"_links":{"self":[{"href":"http:\/\/ee.presscat.kr\/en\/wp-json\/wp\/v2\/ai-in-computer\/118388","targetHints":{"allow":["GET"]}}],"collection":[{"href":"http:\/\/ee.presscat.kr\/en\/wp-json\/wp\/v2\/ai-in-computer"}],"about":[{"href":"http:\/\/ee.presscat.kr\/en\/wp-json\/wp\/v2\/types\/ai-in-computer"}],"wp:featuredmedia":[{"embeddable":true,"href":"http:\/\/ee.presscat.kr\/en\/wp-json\/wp\/v2\/media\/126855"}],"wp:attachment":[{"href":"http:\/\/ee.presscat.kr\/en\/wp-json\/wp\/v2\/media?parent=118388"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}