With the widespread success of artificial intelligence (AI) systems, various applications based on the systems are being applied to our daily life. However, AI systems also raise societal problems since it is highly dependent on training datasets with bias. Consequently, concerning about trustworthiness in AI systems becomes a popular research topic, and recent studies reveal unfairness in developed models. In this paper, we propose a new batch sampling strategy considering fairness among demographic groups. Unlike conventional batch sampling methods such as under-sampling or oversampling, we reflect the notion of fairness directly to estimate the batch sampling probability of data. We empirically demonstrate that our batch sampling method achieves fairer results compared to prior methods in image classification tasks on CelebA and UTKFace datasets.
|Title of host publication||ICTC 2020 - 11th International Conference on ICT Convergence|
|Subtitle of host publication||Data, Network, and AI in the Age of Untact|
|Publisher||IEEE Computer Society|
|Number of pages||4|
|Publication status||Published - 2020 Oct 21|
|Event||11th International Conference on Information and Communication Technology Convergence, ICTC 2020 - Jeju Island, Korea, Republic of|
Duration: 2020 Oct 21 → 2020 Oct 23
|Name||International Conference on ICT Convergence|
|Conference||11th International Conference on Information and Communication Technology Convergence, ICTC 2020|
|Country||Korea, Republic of|
|Period||20/10/21 → 20/10/23|
Bibliographical noteFunding Information:
This research was supported by the MSIT(Ministry of Science and ICT), Korea, under the ITRC(Information Technology Research Center) support program(IITP-2020-2016-0-00464) supervised by the IITP(Institute for Information & communications Technology Planning & Evaluation) and (Artificial Intelligence Graduate School Program(YONSEI UNIVERSITY)) under Grant 2020-0-01361.
© 2020 IEEE.
All Science Journal Classification (ASJC) codes
- Information Systems
- Computer Networks and Communications