@techreport{oai:ipsj.ixsq.nii.ac.jp:00217814,
 author = {Shota, Harada and Seiichi, Uchida and Shota, Harada and Seiichi, Uchida},
 issue = {1},
 month = {May},
 note = {This paper aims to solve the problem of limited annotation in several bio-medical data analysis tasks. Specifically, group-based labeling utilizing constrained clustering and semi-supervised learning are proposed as the approaches. For group-based labeling utilizing constrained clustering, I proposed a new constrained clustering method, where a user attaches annotations to several sample pairs. Annotations are two types: cannot-link and must-link. The pair with cannot-link should not belong to the same cluster, whereas the pair with must-link should belong. These annotations are useful especially for medical data, because medical experts can have a more expected clustering result by a small number of annotations. Moreover, those annotations are treated as soft-constraints and therefore medical experts can attach them without extreme carefulness. For semi-supervised learning in bio-medical data classification tasks, I proposed order-guided disentangled representation learning. This method performs disentangled representation learning with prior knowledge that is effective for learning bio-medical data classification tasks. This method could improve classification performance even with limited annotation by effectively utilizing the prior knowledge through disentangled representation learning., This paper aims to solve the problem of limited annotation in several bio-medical data analysis tasks. Specifically, group-based labeling utilizing constrained clustering and semi-supervised learning are proposed as the approaches. For group-based labeling utilizing constrained clustering, I proposed a new constrained clustering method, where a user attaches annotations to several sample pairs. Annotations are two types: cannot-link and must-link. The pair with cannot-link should not belong to the same cluster, whereas the pair with must-link should belong. These annotations are useful especially for medical data, because medical experts can have a more expected clustering result by a small number of annotations. Moreover, those annotations are treated as soft-constraints and therefore medical experts can attach them without extreme carefulness. For semi-supervised learning in bio-medical data classification tasks, I proposed order-guided disentangled representation learning. This method performs disentangled representation learning with prior knowledge that is effective for learning bio-medical data classification tasks. This method could improve classification performance even with limited annotation by effectively utilizing the prior knowledge through disentangled representation learning.},
 title = {Bio-Medical Data Classification Approaches with Limited Annotation},
 year = {2022}
}