Unsupervised Kernel-based Multi-view Feature Selection with Robust Self-representation and Binary Hashing
Authors: Rongyao Hu, Jiangzhang Gan, Mengmeng Zhan, Li Li, Mengling Wei
AAAI 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Comprehensive experiments on public multi-view datasets indicate that our proposed method achieves state-of-the-art performance compared with the representative comparison methods regarding the clustering and the feature selection task. Experiments are tested on public multi-view datasets, which have proved the superior result of the proposed method for unsupervised multi-view feature selection task. |
| Researcher Affiliation | Academia | 1 School of Computer Science and Technology, University of Electronic Science and Technology of China, Chengdu 611731, China 2 Knowledge and Data Engineering Laboratory of Chinese Medicine, School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu 610054, China 3 School of Computer Science and Technology, Hainan University, Haikou 570228, China 4 Computer School, Beijing Information Science and Technology University, Beijing 100101, China EMAIL, EMAIL, EMAIL, EMAIL, ml EMAIL |
| Pseudocode | No | The paper describes an "effective optimization scheme is proposed" and "a novel optimization algorithm is conducted to solve the proposed method" but does not include structured pseudocode or an algorithm block. |
| Open Source Code | No | The paper does not provide any statement regarding the availability of source code or a link to a code repository. |
| Open Datasets | Yes | In this section, six multi-view datasets are tested, including Caltech101 1, HW 2, MSRCV1 (Yang et al. 2024a), Scene (Shi et al. 2023), ORL 3, and Web KB 4. 1http://www.vision.caltech.edu/Image Datasets/Caltech101/.. 2https://archive.ics.uci.edu/dataset/72/multiple+features.. 3https://www.kaggle.com/datasets/tavarez/the-orl-databasefor-training-and-testing. 4http://www.webkb.org/. |
| Dataset Splits | No | The paper mentions 'Feature rates' for selected features (e.g., 10%, 15%) but does not specify how the datasets are split into training, validation, or test sets for reproducibility. |
| Hardware Specification | No | The paper does not provide any specific hardware details such as GPU/CPU models, processor types, or memory used for running the experiments. |
| Software Dependencies | No | The paper mentions using 'K-means' but does not provide specific version numbers for this or any other software dependencies, libraries, or solvers used in the experiments. |
| Experiment Setup | Yes | For the proposed method, the parameters α, β and γ are adjusted from {10 2, ..., 102} by the grid-search way, the length of hash codes l is selected from {4, 8, 16, 32, 64}, the low-rank r is defined as the range of min{n, s}. For the operation ϕ, η is set to 0.5, and anchor number s is set to one value from the range of {100, 1000} based on the order to magnitude of the samples for each dataset. |