Sample-Level Cross-View Similarity Learning for Incomplete Multi-View Clustering

Authors: Suyuan Liu, Junpu Zhang, Yi Wen, Xihong Yang, Siwei Wang, Yi Zhang, En Zhu, Chang Tang, Long Zhao, Xinwang Liu

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

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results on six benchmark datasets demonstrate the ability of SCSL in processing incomplete multi-view clustering tasks. Our code is publicly available at https://github.com/Tracesource/SCSL. Experiments Experimental Settings Datasets We evaluate the effectiveness of the proposed algorithm using six widely used datasets: MSRCV, ORL, Protein Fold, Wiki, CCV, and SUNRGBD.
Researcher Affiliation Academia 1 School of Computer, National University of Defense Technology, Changsha, China, 410073 2 Intelligent Game and Decision Lab, Beijing, China, 100091 3 School of Computer Science, China University of Geosciences, Wuhan, China, 430074 4 Shandong Computer Science Center, Qilu University of Technology, Jinan, China, 250000
Pseudocode Yes Algorithm 1: SCSL
Open Source Code Yes Our code is publicly available at https://github.com/Tracesource/SCSL.
Open Datasets Yes We evaluate the effectiveness of the proposed algorithm using six widely used datasets: MSRCV, ORL, Protein Fold, Wiki, CCV, and SUNRGBD.
Dataset Splits No The paper mentions generating incomplete datasets and searching for hyperparameters but does not provide specific details on training, validation, or test splits (e.g., percentages or counts).
Hardware Specification Yes All experiments were conducted on a desktop computer equipped with an Intel Core i9-10900X CPU, 64GB of RAM, and MATLAB 2020b (64-bit).
Software Dependencies Yes All experiments were conducted on a desktop computer equipped with an Intel Core i9-10900X CPU, 64GB of RAM, and MATLAB 2020b (64-bit).
Experiment Setup Yes For all the aforementioned algorithms, we configured their parameters within their recommended ranges. In our proposed method, we search β in [0.001, 1, 10] and λ in [0.001, 0.1, 1].