Variational Label Enhancement

Authors: Ning Xu, Jun Shu, Yun-Peng Liu, Xin Geng

ICML 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental The recovery experiment on fourteen label distribution datasets and the predictive experiment on ten multi-label learning datasets validate the advantage of our approach over the state-of-the-art approaches.
Researcher Affiliation Academia 1School of Computer Science and Engineering, Southeast University, Nanjing 210096, China 2School of Mathematics and Statistics, Xi an Jiaotong University, Xi an 710049, China.
Pseudocode No The paper does not contain any structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide an explicit statement about releasing source code for the described methodology, nor does it provide a direct link to a code repository.
Open Datasets Yes There are in total one artificial dataset and 13 real-world label distribution datasets1. These real-world datasets (Geng, 2016) collected from biological experiments on the yeast genes, facial expression images, natural scene images and movies, respectively. (1http://palm.seu.edu.cn/xgeng/LDL/index.htm) There are ten MLL datasets2 used in the experiments. (2mulan.sourceforge.net/datasets.html)
Dataset Splits Yes All the algorithms are tested via ten-fold cross validation.
Hardware Specification No The paper does not explicitly describe the hardware used to run its experiments.
Software Dependencies No The paper mentions general methods and model architectures (e.g., MLPs, SGD, Ada Grad) but does not provide specific version numbers for any software dependencies like programming languages or libraries.
Experiment Setup Yes For LEVI, the MLPs are constructed with three hidden layers, each with 500 hidden units and softplus activation functions.