Learning from Label Proportions with Generative Adversarial Networks
Authors: Jiabin Liu, Bo Wang, Zhiquan Qi, YingJie Tian, Yong Shi
NeurIPS 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Several experiments on benchmark datasets demonstrate vivid advantages of the proposed approach. |
| Researcher Affiliation | Collaboration | Jiabin Liu Samsung Research China Beijing Beijing 100028, China liujiabin008@126.com Bo Wang University of International Business and Economics Beijing 100029, China wangbo@uibe.edu.cn Zhiquan Qi Yingjie Tian Yong Shi University of Chinese Academy of Sciences Beijing 100190, China qizhiquan@foxmail.com, {tyj,yshi}@ucas.ac.cn |
| Pseudocode | Yes | Algorithm 1: LLP-GAN Training Algorithm |
| Open Source Code | Yes | Code is available at https://github.com/liujiabin008/LLP-GAN. |
| Open Datasets | Yes | Four benchmark datasets, MNIST, SVHN, CIFAR-10, and CIFAR-100 are investigated in our experiments. |
| Dataset Splits | Yes | In the experimental setting, the training data is equally divided into five minibatches, with 10,000 images in each one, and the test data with exactly 1,000 images in every category. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., GPU/CPU models, memory) used for running its experiments. |
| Software Dependencies | No | The paper does not provide specific ancillary software details (e.g., library or solver names with version numbers) needed to replicate the experiment. |
| Experiment Setup | Yes | To keep up the same settings in previous work, bag size is fixed as 16, 32, 64, and 128. |