Multiple Medoids based Multi-view Relational Fuzzy Clustering with Minimax Optimization
Authors: Yangtao Wang, Lihui Chen, Xiao-Li Li
IJCAI 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experimental studies on several multi-view data sets including real world image and document data sets demonstrate that M4-FC not only outperforms single medoid based multi-view fuzzy clustering approach, but also performs better than existing multi-view relational clustering approaches. |
| Researcher Affiliation | Collaboration | Yangtao Wang1, Lihui Chen2, Xiaoli Li1 1Institude for Infocomm Research(I2R), A*STAR, Singapore 2School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore |
| Pseudocode | Yes | Algorithm 1: Input: Distance matrix of P views R1 n n, ..., RP n n, number of clusters K, parameter Tu, Tv,γ stopping criterion ϵ Output: Consensus Fuzzy membership matrix U , representative weight matrix of each view V (p) Method: |
| Open Source Code | No | The paper does not provide an explicit statement or a link to open-source code for the described methodology. |
| Open Datasets | Yes | Multiple features (MF)1: https://archive.ics.uci.edu/ml/data sets/Multiple+Features. Image segmentation (IS) 2: https://archive.ics.uci.edu/ml/data sets/Image+Segmentation. Oxford Flowers 3: http://www.robots.ox.ac.uk/ vgg/data/flowers/17/index.html. 3-Sources document (3-S) 4: http://mlg.ucd.ie/data sets/3sources.html. Reuters multilingual: This data set consists of documents written in five different languages (English, French, German, Spanish and Italian) and their corresponding translations [Amini et al., 2009]. |
| Dataset Splits | No | The paper describes initialization methods for medoids and states that 'the initialization of each run is the same, therefore the clustering results are the same for each run', but it does not specify any train/validation/test dataset splits, percentages, or absolute sample counts for data partitioning used for evaluation. |
| Hardware Specification | No | The code is implemented in MATLAB and runs on a computer with eight cores and eight gigabytes of memory. |
| Software Dependencies | No | The code is implemented in MATLAB and runs on a computer with eight cores and eight gigabytes of memory. |
| Experiment Setup | Yes | For fair comparison, the parameter m in FCMD, Con FCMD and MVFCMdd V is searched from the range of [1.1 2] with step 0.1. For MVSC, we follow the authors experimental setting and parameter selecting methods in their paper. For M4-FC, the parameter γ is searched from [0.1 0.9] with the step 0.1. Tu is searched from [0.001, 0.003, 0.01, 0.03, 0.1, 0.3]. Tv is set by a guideline to make Tu/K and Tv/N close to each other or be in the same order which always produces reasonable results in our experimental study. |