Binary Classification from Multiple Unlabeled Datasets
               via Surrogate Set Classification

            Nan Lu * 1 2 Shida Lei * 1 Gang Niu 2 Issei Sato 1 2 Masashi Sugiyama 2 1

             Abstract                 et al., 2017; Van Rooyen & Williamson, 2018; Han et al.,
   To cope with high annotation costs, training a        2018; 2020; Fang et al., 2020; Xia et al., 2020), partial la-
   classifier only from weakly supervised data has       bels (Cour et al., 2011; Ishida et al. ...