Tensor-SVD Based Graph Learning for Multi-View Subspace Clustering
Authors: Quanxue Gao, Wei Xia, Zhizhen Wan, Deyan Xie, Pu Zhang3930-3937
AAAI 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experimental results reveal that our WTNNM method is superior to several state-of-the-art multi-view subspace clustering methods in terms of performance. |
| Researcher Affiliation | Academia | Quanxue Gao,1 Wei Xia,1 Zhizhen Wan,1 Deyan Xie,1 Pu Zhang1 1State Key Laboratory of Integrated Services Networks, Xidian University, Xi an 710071, China. |
| Pseudocode | Yes | Algorithm 1 WTNNM for Multi-view clustering |
| Open Source Code | No | The paper does not provide concrete access to source code for the methodology described (e.g., no specific repository link, explicit code release statement, or code in supplementary materials). |
| Open Datasets | Yes | Yale1 face database has 165 grayscaling images of 15 persons. Just as (Luo et al. 2018), we extract three types of features: 4096 dimensions intensity feature, 3304 LBP feature, and 6750 dimensions Gabor feature. 1http://vision.ucsd.edu/content/yale-face-database and Caltech-101 database2 contains 8677 images of objects belonging to 101 categories... 2http://www.vision.caltech.edu/Image Datasets/Caltech101/ |
| Dataset Splits | No | The paper does not provide specific dataset split information (exact percentages, sample counts, citations to predefined splits, or detailed splitting methodology) for training, validation, or testing. |
| Hardware Specification | No | The paper does not provide specific hardware details (exact GPU/CPU models, processor types with speeds, memory amounts, or detailed computer specifications) used for running its experiments. |
| Software Dependencies | No | The paper does not provide specific ancillary software details (e.g., library or solver names with version numbers like Python 3.8, CPLEX 12.4) needed to replicate the experiment. |
| Experiment Setup | Yes | Parameter Setting In our experiments, we tune the parameter λ in the range of [0.0001, 0.0005, 0.001, 0.005, 0.01, 0.05, 0.1, 0.5, 1, 5, 10, 100], and the weight ωi (0, 100] to get the best results. Specifically, λ is set to 1, the weight vector ω is set to (1; 10; 100) on Yale dataset; λ is set to 0.5, the weight vector ω is set to (1; 10; 100) on Notting-Hill dataset; λ is set to 0.01, the weight vector ω is set to (0.5; 5; 10) on Caltech-101 dataset; λ is set to 0.01, the weight vector ω is set to (1; 10; 100) on UCI-Digits dataset; λ is set to 0.005, the weight vector ω is set to (0.5; 1; 5) on Scene-15 dataset. |