NeurIPS 2019
Sun Dec 8th through Sat the 14th, 2019 at Vancouver Convention Center
Paper ID:3901
Title:Learning from Label Proportions with Generative Adversarial Networks

All three reviewers agreed that the idea of using adversarial learning for learning from label proportions is novel and interesting. For the final version, we would recommend the proposed method to be validated on: 1) structured and non-random bag assignment setting (e.g. Patrini et al., (Almost) no label no cry, NIPS 2014); 2) tabular data.