Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1].
Incomplete and Unpaired Multi-View Graph Clustering with Cross-View Feature Fusion
Authors: Liang Zhao, Ziyue Wang, Xiao Wang, Zhikui Chen, Bo Xu
AAAI 2025 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | The experiments on incomplete and unpaired multi-view datasets demonstrate that MGCCFF outperforms state-of-the-art methods. ... Extensive experiments under various conditions verify the advantages of our proposed model MGCCFF. Compared with existing state-of-the-art methods, our model shows clearly superior performance on incomplete and unpaired multi-view data. |
| Researcher Affiliation | Academia | Liang Zhao, Ziyue Wang, Xiao Wang, Zhikui Chen, Bo Xu Dalian University of Technology, Dalian, China EMAIL, EMAIL, Alan Wang EMAIL |
| Pseudocode | Yes | Algorithm 1: The proposed MGCCFF |
| Open Source Code | No | The paper does not contain an explicit statement about releasing source code for the described methodology, nor does it provide a link to a code repository. |
| Open Datasets | Yes | Datasets We evaluate our model MGCCFF on datasets with 50%, 70% complete rates and 10%, 30%, 50%, 70% paired rates including Handwritten (Zhang et al. 2020a) ... BDGP (Cai et al. 2012) ... Caltech101-20 (Li et al. 2015) ... BBCSport (Luo et al. 2018) ... Yale (Luo et al. 2018) |
| Dataset Splits | No | The paper mentions 'different complete rates and paired rates' (e.g., 50%, 70% complete and 10%, 30%, 50%, 70% paired) to generate data scenarios, but it does not specify explicit training/test/validation splits or cross-validation strategies. For clustering tasks, evaluation is often done on the entire dataset, but no specific partitioning details are provided. |
| Hardware Specification | Yes | All the following experiments are implemented using sklearn library and Py Torch library on a windows 10 OS with an NVIDIA 3090 GPU. |
| Software Dependencies | No | The paper mentions 'sklearn library' and 'Py Torch library' but does not specify their version numbers, which is necessary for reproducible software dependencies. |
| Experiment Setup | No | The paper describes the overall framework and steps in Algorithm 1, including inputs like 'cluster number K, epoch E'. However, it does not provide concrete numerical values for hyperparameters such as K, E, learning rates, batch sizes, or optimizer settings used in the experiments. It outlines the general experimental settings and metrics but lacks specific configuration details. |