Towards Resource-friendly, Extensible and Stable Incomplete Multi-view Clustering

Authors: Shengju Yu, Zhibin Dong, Siwei Wang, Xinhang Wan, Yue Liu, Weixuan Liang, Pei Zhang, Wenxuan Tu, Xinwang Liu

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

Reproducibility Variable Result LLM Response
Research Type Experimental Many results suggest that To RES exhibits advantages against 20 SOTA algorithms, even in scenarios with a higher ratio of incomplete data.
Researcher Affiliation Academia 1School of Computer, National University of Defense Technology, Changsha, Hunan, China 2Intelligent Game and Decision Lab, Beijing, China. yu-shengju@foxmail.com. Correspondence to: Siwei Wang <wangsiwei13@nudt.edu.cn>, Xinwang Liu <xinwangliu@nudt.edu.cn>.
Pseudocode Yes Algorithm 1 Scheme 1 for solving Eq. (4) Algorithm 2 Scheme 2 for solving Eq. (4) Algorithm 3 To RES
Open Source Code No The paper does not contain an explicit statement or link indicating that the source code for the described methodology is publicly available.
Open Datasets Yes Six widely-used datasets are adopted in experiments, including small-scale datasets: Webkb, Wikifea; middle-scale datasets: AWA10, SUNRGB-D; large-scale datasets: Aw Afea, EMNIST. Table 3 describes their details. ... H. The URLs of Benchmark Datasets ... Webkb: https://www.cs.cmu.edu/ webkb/ Wikifea: http://svcl.ucsd.edu/projects/crossmodal/ AWA10: https://cvml.ista.ac.at/Aw A2/ SUNRGB-D: https://rgbd.cs.princeton.edu/ Aw Afea: https://cvml.ista.ac.at/Aw A/ EMNIST: https://www.nist.gov/itl/products-and-services/emnist-dataset
Dataset Splits No The paper mentions evaluating under different "percentage of incomplete data (PID)" (20%, 40%, 60%) but does not provide specific train/validation/test dataset splits, percentages, or sample counts.
Hardware Specification No The paper does not provide any specific details about the hardware used to run the experiments, such as CPU models, GPU models, or memory specifications.
Software Dependencies No The paper does not list specific software dependencies with version numbers (e.g., Python, PyTorch, TensorFlow versions, or other libraries/solvers).
Experiment Setup No The paper mentions its method aims to "eliminate hyper-parameters" but does not provide specific hyperparameter values or detailed system-level training settings for its own method or the baselines compared. There is no dedicated section or table detailing the experimental setup with concrete configuration parameters.