Efficient Multi-view Clustering via Reinforcement Contrastive Learning

Authors: Qianqian Wang, Haiming Xu, Zihao Zhang, Zhiqiang Tao, Quanxue Gao

IJCAI 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experimental results showcase the effectiveness and superiority of our proposed method on multiple benchmark datasets. ... 4 Experiment 4.1 Datasets & Metric 4.2 Experiment Setup 4.3 Performance Comparison 4.4 Hyper-parameter Analysis 4.5 Ablation Studies 4.6 Visualization Analysis 4.7 Convergence Analysis
Researcher Affiliation Academia 1School of Telecommunications Engineering, Xidian University, Xi an, China 2Department of Computer Science, Rochester Institute of Technology, Rochester, NY, USA
Pseudocode No The paper describes the methodology in prose and mathematical formulations within section 3, but does not present any structured pseudocode or algorithm blocks.
Open Source Code No The paper states 'implemented using Py Torch (Python 3.10.13)' but does not provide any explicit statement about releasing the source code or a link to a repository for the methodology described.
Open Datasets Yes We evaluate our method on six real-world multi-view datasets from previous works [Chen et al., 2023; Xu et al., 2023]: COIL-20 with 1,440 grayscale images of 20 objects from different angles, RGB-D containing 1,449 samples with RGB and depth information, BDGP consisting of 2,500 drosophila embryo images with two visual descriptors, Scene-15 including 4,485 scene images with GIST, LBP, and HOG features, MNIST-USPS combining handwritten digit samples from both datasets, and Fashion containing product images with visual, textual, and categorical features.
Dataset Splits No The paper lists the datasets used and evaluation metrics, but it does not explicitly provide details about how these datasets were split into training, test, or validation sets for reproducibility.
Hardware Specification Yes All experiments were conducted on an NVIDIA Ge Force RTX 4090 GPU with CUDA 12.4, implemented using Py Torch (Python 3.10.13).
Software Dependencies Yes All experiments were conducted on an NVIDIA Ge Force RTX 4090 GPU with CUDA 12.4, implemented using Py Torch (Python 3.10.13).
Experiment Setup No The paper discusses the sensitivity of hyperparameters λ and β and mentions other parameters like αt, τ1, αc, ηe, ηc, τ, and γ in the methodology. However, it does not provide a specific set of values for these hyperparameters that were used to achieve the reported experimental results in the performance comparison table.