Simple Contrastive Multi-View Clustering with Data-Level Fusion
Authors: Caixuan Luo, Jie Xu, Yazhou Ren, Junbo Ma, Xiaofeng Zhu
IJCAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | 3 Experiment |
| Researcher Affiliation | Academia | School of Computer Science and Engineering, Guangxi Normal University, Guilin 541004, China 2Guangxi Key Lab of Multi-source Information Mining & Security, Guilin 541004, China 3School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China 4School of Communication Engineering, Hangzhou Dianzi University, Hangzhou 310018, China |
| Pseudocode | Yes | Algorithm 1: The training steps of SCM framework |
| Open Source Code | Yes | Our SCM is implemented by Py Torch and its code is available in https://github.com/Submissions In/SCM. |
| Open Datasets | Yes | Datasets We conduct experiments on 8 public datasets, including BDGP [Cai et al., 2012], DIGIT [Peng et al., 2019], Fashion [Xiao et al., 2017], NGs [Hussain et al., 2010], VOC [Everingham et al., 2010], Web KB [Sun et al., 2007], DHA [Lin et al., 2012], and COIL-20 [Nene et al., 1996]. |
| Dataset Splits | No | The paper specifies training and testing of the model but does not explicitly provide details about a distinct validation set split or its size/proportion. |
| Hardware Specification | No | The paper does not provide specific hardware details such as GPU or CPU models, or memory specifications used for experiments. |
| Software Dependencies | No | The paper states that "Our SCM is implemented by Py Torch" and "The optimizer was Adam [Kingma and Ba, 2014]" but does not provide specific version numbers for these software components. |
| Experiment Setup | Yes | For all datasets used in our experiments, the dimensions of H, Z, and Q were set to 256, 128, and 64, respectively. The optimizer was Adam [Kingma and Ba, 2014] with a learning rate of 0.0003, and the batch size was set to 256. Both the noise and missing rates of multi-view data augmentation were set to 0.25, and the noise variance was 0.4. |