讲座题目：Learning from Label Proportions with Generative Adversarial Networks
主讲人：齐志泉副研究员 中国科学院虚拟经济与数据科学研究中心
讲座时间：2021年12月10日（周五）14：00-15：30
讲座地点：中国科学院大学中关村校区教学楼S406；腾讯会议ID:489 999 758
内容摘要：In this paper, we leverage generative adversarial networks (GANs) to derive an effective algorithm LLP-GAN for learning from label proportions (LLP), where only the bag-level proportional information in labels is available. Endowed with end-to-end structure, LLP-GAN performs approximation in the light of an adversarial learning mechanism, without imposing restricted assumptions on distribution. Accordingly, we can directly induce the final instance-level classifier upon the discriminator. Under mild assumptions, we give the explicit generative representation and prove the global optimality for LLP-GAN. Additionally, compared with existing methods, our work empowers LLP solver with capable scalability inheriting from deep models. Several experiments on benchmark datasets demonstrate vivid advantages of the proposed approach.
主讲人简介：齐志泉，中国科学院虚拟经济与数据科学研究中心副研究员。长期从事机器学习方法及应用方面研究。 在国内外主流期刊上（如：IEEE Trans. Neural Networks and Learning、IEEE Trans. Image Processing 、 IEEE Trans. Cybernetics、IEEE Trans. Intelligent Transportation Systems、 Neural Networks、Pattern Recognition发表SCI文章30余篇，国际会议（如：NeurlPS、AAAI、 IJCAI在内的CCF， A类国际顶会等）10余篇。 Google学术引用2000余次。
