Unsupervised Feature Selection by Pareto Optimization

Authors: Chao Feng, Chao Qian, Ke Tang3534-3541

AAAI 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Empirical results exhibit the superior performance of POCSS over the state-of-the-art algorithms. In this section, we empirically evaluate the effectiveness of POCSS on 10 real-world data sets
Researcher Affiliation Academia 1Anhui Province Key Lab of Big Data Analysis and Application, School of Computer Science and Technology, University of Science and Technology of China, Hefei 230027, China 2Shenzhen Key Lab of Computational Intelligence, Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen 518055, China
Pseudocode Yes Algorithm 1 POCSS Algorithm; Algorithm 2 Evaluation Subprocedure
Open Source Code No The paper does not provide any statement about making the source code available or a link to a code repository.
Open Datasets Yes The data sets are downloaded from http://archive.ics.uci.edu/ ml/ and http://www.csie.ntu.edu.cn/ cjlin/libsvmtools/datasets/.
Dataset Splits No The paper uses '10 real-world data sets' and compares algorithms, but does not explicitly state how these datasets were split into training, validation, or test sets.
Hardware Specification No The paper does not specify any hardware details such as CPU or GPU models used for the experiments.
Software Dependencies No The paper does not list any specific software dependencies with version numbers.
Experiment Setup Yes For Two-stage, 2k columns are selected in the randomized stage. For WA , we implement its best version WA -b and set the parameter ϵ = 0.5. For POCSS, the number of iterations is ekn(n + 1) as suggested by Theorem 1. To improve its efficiency, submatrices with at least 2k columns are excluded in the running process, thus the number of iterations is set to 2ek2n.