Contrastive and View-Interaction Structure Learning for Multi-view Clustering

Authors: Jing Wang, Songhe Feng

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

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments conducted on six benchmarks illustrate the superiority of our method compared to other state-of-the-art approaches.
Researcher Affiliation Academia 1Key Laboratory of Big Data & Artificial Intelligence in Transportation (Beijing Jiaotong University), Ministry of Education 2School of Computer Science and Technology, Beijing Jiaotong University, Beijing 100044, China
Pseudocode Yes The whole learning process of SERIES is summarized in the Algorithm 1.
Open Source Code No The paper does not provide any statement or link indicating that the source code for the described methodology is publicly available.
Open Datasets Yes Datasets. The following datasets are carried out for evaluation: (1) HW [Perkins and Theiler, 2003]... (2) Reuters [Amini et al., 2009]... (3) Noisyminist [Wang et al., 2015]... (4) VOC [Hwang and Grauman, 2010]... (5) Hdigit [Chen et al., 2022]... (6) Mfeat [Wang et al., 2019]...
Dataset Splits No The paper describes training and fine-tuning epochs but does not specify any explicit training/validation/test dataset splits, sample counts for each split, or cross-validation setup.
Hardware Specification Yes All experiments are conducted on a Linux platform utilizing an Intel(R) Core(TM) i9-11900 2.50GHz CPU, 64GB RAM, and Ge Force RTX 3090 Ti GPU.
Software Dependencies No The paper mentions software components like 'Re LU' (activation function) and 'Adam' (optimizer), but does not provide specific version numbers for these or any other software libraries or frameworks used.
Experiment Setup Yes The view-specific deep graph autoencoders are pre-trained for 200 epochs, and the entire model is fine-tuned for an additional 100 epochs. The dimensions of the encoders, decoders, and the cross dual relation generation layer are set to {dv, 512, 2048, 256}, {256, 2048, 512, dv} and {256, dv} respectively. The activation function is specified as Re LU. In our study, the trade-off hyperparameters λ1, λ2 are selected from the range {0.1, 0.2, . . . , 0.9, 1.0}.