Efficient Multi-view Unsupervised Feature Selection with Adaptive Structure Learning and Inference

Authors: Chenglong Zhang, Yang Fang, Xinyan Liang, Han Zhang, Peng Zhou, Xingyu Wu, Jie Yang, Bingbing Jiang, Weiguo Sheng

IJCAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental In this section, six real-word datasets are employed, including flower-171, Leaves2, NUS3, Scene4, ALOI5 and Youtube6. The details of each dataset are listed in Table 2. To comprehensively verify the superiority and effectiveness of EMUFS, we conduct experiments with six state-of-the-art competitors, including (1) Unsupervised Feature Selection with Structured Graph Optimization (SOGFS) [Nie et al., 2016]; (2) Multi View Clustering and Feature Learning via Structured Sparsity (MVCSS) [Wang et al., 2013]; (3) Multi-view Unsupervised Feature Selection with Adaptive Similarity and View Weight (ASVW) [Hou et al., 2017]; (4) Multi-view Feature Selection via Nonnegative Structured Graph Learning (NSGL) [Bai et al., 2020]; (5) Multilevel Projections with Adaptive Neighbor Graph for Unsupervised Multi-View Feature Selection (MAMFS) [Zhang et al., 2021]; (6) Robust Unsupervised Feature Selection via Multi-Group Adaptive Graph Representation (MGAGR) [You et al., 2023]. To ensure comparison fairness, the parameters of all competitors are tuned following their respective works. The regularization parameters for EMUFS are searched in a grid of {10 3, 10 2, , 103}, with the number of anchors set as m = 10% n. The Kmeans clustering is independently executed 20 times on the selected feature subsets, and the average results, including the clustering accuracy (ACC) and the normalized mutual information (NMI), are reported to evaluate the performance.
Researcher Affiliation Academia 1Hangzhou Normal University, Hangzhou, China 2Chongqing University of Posts and Telecommunications, Chongqing, China 3Shanxi University, Taiyuan, China 4Northwestern Polytechnical University, Xi an, China 5Anhui University, Hefei, China 6Hong Kong Polytechnic University, Hong Kong SAR, China 7University of Technology Sydney, NSW, Australia
Pseudocode Yes Algorithm 1 Optimization procedures for EMUFS
Open Source Code No The paper does not contain any explicit statement about making the source code for EMUFS publicly available, nor does it provide a link to a code repository.
Open Datasets Yes In this section, six real-word datasets are employed, including flower-171, Leaves2, NUS3, Scene4, ALOI5 and Youtube6. The details of each dataset are listed in Table 2. 1https://www.robots.ox.ac.uk/ vgg/data/flowers/ 2https://archive.ics.uci.edu/dataset/ 3https://lms.comp.nus.edu.sg/wpcontent/uploads/2019/research/nuswide/NUS-WIDE.html 4http://people.csail.mit.edu/torralba/code/spatialenvelope/ 5https://aloi.science.uva.nl/ 6https://archive.ics.uci.edu/dataset/269/
Dataset Splits No The paper uses datasets and evaluates performance, and mentions "The Kmeans clustering is independently executed 20 times on the selected feature subsets", and "running times versus the training sample scale", but it does not provide explicit details about train/validation/test dataset splits or cross-validation setup.
Hardware Specification No The paper does not specify any hardware details (like specific CPU/GPU models or memory) used for running the experiments.
Software Dependencies No The paper does not specify any software dependencies with version numbers (e.g., programming languages, libraries, frameworks) used for implementation.
Experiment Setup Yes The regularization parameters for EMUFS are searched in a grid of {10 3, 10 2, , 103}, with the number of anchors set as m = 10% n.