M$^3$Fair: Mitigating Bias in Healthcare Data through Multi-Level and Multi-Sensitive-Attribute Reweighting Method

Authors:

Yinghao Zhu $^{[1,2,†]}$, Jingkun An $^{[2,3,†]}$, Enshen Zhou $^{[2,3]}$, Lu An $^{[4]}$, Junyi Gao $^{[5,6]}$, Hao Li $^{[2,3]}$, Haoran Feng $^{[2,3]}$, Bo Hou $^{[2,3]}$, Wen Tang $^{[7]}$, Chengwei Pan $^{[1,*]}$, Liantao Ma $^{[2,*]}$

Affiliations:

• $^{[1]}$ Institute of Artificial Intelligence, Beihang University, Beijing, China
• $^{[2]}$ National Engineering Research Center for Software Engineering, Peking University, Beijing, China
• $^{[3]}$ School of Software, Beihang University, Beijing, China
• $^{[4]}$ Department of Electrical and Computer Engineering, North Carolina State University, North Carolina, USA
• $^{[5]}$ Institute of Genetics and Cancer, University of Edinburgh, Edinburgh, UK
• $^{[6]}$ Health Data Research UK, UK
• $^{[7]}$ Department of Nephrology, Peking University Third Hospital, Beijing, China

*Address correspondence to: [email protected] (C.P.); [email protected] (L.M.), †These authors contributed equally to this work.