Anchor Learning with Potential Cluster Constraints for Multi-view Clustering
Authors: Yawei Chen, Huibing Wang, Jinjia Peng, Yang Wang
AAAI 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments on six benchmark datasets demonstrate the effectiveness of our proposed method compared to some state-of-the-art MVC methods. |
| Researcher Affiliation | Academia | 1School of Information Science and Technology, Dalian Martime University, Dalian, China 2School of Cyber Security and Computer, Hebei University, Baoding, China 3School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China EMAIL, EMAIL, EMAIL |
| Pseudocode | Yes | Algorithm 1: ALPC algorithm Input: Multi-view data {X(v)}l v=1, cluster number k, parameters λ1, λ2, m; Initialize: A(v)= 0, U(v)= 0, P = 0, R = 0 Output: Perform k-means on Z to obtain the clusters. 1: while not converged do 2: Update variable A(v) using Eq. (7); 3: Update variable Z using Eq. (9); 4: Update variable P using Eq. (11); 5: Update variable R using Eq. (13); 6: Update variable U(v) using Eq. (15); 7: end while |
| Open Source Code | Yes | Code https://github.com/whbdmu/ALPC |
| Open Datasets | Yes | The datasets used in the experiments include MSRC (Chen et al. 2021), BBCSport1, Wiki2, Caltech1013, MNIST4 and You Tube Face sel5. ... 1http://mlg.ucd.ie/datasets/bbc.html 2http://www.svcl.ucsd.edu/projects/crossmodal/ 3https://paperswithcode.com/dataset/caltech-101 4https://yann.lecun.com/exdb/mnist/ 5http://www.cs.tau.ac.il/ wolf/ytfaces/ |
| Dataset Splits | No | We validate the well-behaved performance of ALPC using six benchmark datasets, where the maximum number of samples used is more than 100,000. ... For a fair comparison, we used the official codes of the corresponding methods and ran K-means 50 times to get the best results. No specific train/test/validation splits for the model learning or evaluation are mentioned beyond using the entire datasets for clustering and running K-means for robust evaluation. |
| Hardware Specification | No | The paper mentions comparing computation time, but does not provide specific details about the hardware (e.g., GPU/CPU models, memory) used for running the experiments. |
| Software Dependencies | No | No specific software dependencies with version numbers are mentioned in the paper. |
| Experiment Setup | Yes | For the methods in this paper, we adjust the values of λ1 and λ2 in 10 2, 10 1, ...102 , 10 4, ..., 10 1, 1 . In addition, we also find that the number of anchors has a very large impact on the clustering performance. Obviously, most datasets perform best when the number of anchors is 2c or 3c. |