Active Deep Multi-view Clustering

Authors: Helin Zhao, Wei Chen, Peng Zhou

IJCAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental The extensive experiments on benchmark data sets show that our method can outperform stateof-the-art unsupervised and semi-supervised methods, demonstrating the effectiveness and superiority of the proposed method.
Researcher Affiliation Academia Helin Zhao1 , Wei Chen1 , Peng Zhou1 1Anhui Provincial International Joint Research Center for Advanced Technology in Medical Imaging, School of Computer Science and Technology, Anhui University {e21201088, e23201102}@stu.ahu.edu.cn, zhoupeng@ahu.edu.cn
Pseudocode Yes Algorithm 1 Active Deep Multi-view Clustering
Open Source Code Yes The code is available at https://github.com/wodedazhuozi/ADMC.
Open Datasets Yes To validate the effectiveness of ADMC, we conduct experiments on eight benchmark data sets, including BBCSport 1 , Caltech-2V [Fei-Fei et al., 2004], Caltech-5V [Fei-Fei et al., 2004], CCV [Jiang et al., 2011], Reuters1200 [Amini et al., 2009], Cora [Wen et al., 2020], Scene [Fei-Fei and Perona, 2005], and Noisy-Mnist 2. 1http://mlg.ucd.ie/datasets/ 2https://github.com/nineleven/Noisy MNISTDetection
Dataset Splits No The paper mentions 'train' and 'validation' in the JSON schema but does not provide specific details on how the datasets were split into training, validation, and testing sets (e.g., percentages, sample counts, or references to predefined splits).
Hardware Specification Yes All experiments are conducted on the PC with AMD Ryzen 7 7840H CPU, NVIDIA Ge Force RTX 4060 GPU, and 16GB RAM.
Software Dependencies No The paper mentions 'Adm W as the optimizer' but does not specify version numbers for any software dependencies, libraries, or programming languages used.
Experiment Setup Yes For our proposed ADMC, the sizes of the four hidden layers in the auto-encoder are set to 500, 500, 2000, and 128, respectively. The FC in the fusion module is a four-layer MLP with RELU as an active function whose sizes are set to 128, 128, 256, and 1, respectively. The FC in the supervised module is a single layer whose size is the number of clusters. α is fixed as 10 5, and β and γ are chosen from [10 3, 103]. τ is fixed as 0.6. We use Adm W as the optimizer, The experiments contain 5 selection batches and the budget of each batch is 10 samples.