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 Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers," Under Review, 2026..
Incomplete Multi-view Deep Clustering with Data Imputation and Alignment
Authors: Jiyuan Liu, Xinwang Liu, Xinhang Wan, KE LIANG, Weixuan Liang, sihang zhou, Huijun Wu, Kehua Guo
NeurIPS 2025 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | In experiment, the proposed method is validated on a set of benchmark datasets and achieves state-of-the-art performances. |
| Researcher Affiliation | Academia | 1 National University of Defense Technology, Changsha, Hunan, China. 410072. 2 Central South University, Changsha, Hunan, China. 410083. EMAIL |
| Pseudocode | Yes | Algorithm 1 Incomplete Multi-view Deep Clustering with Data Imputation and Alignment |
| Open Source Code | Yes | The code is available at https://github.com/liujiyuan13/IMDC-DIA-code_release. |
| Open Datasets | Yes | To validate the proposed IMDC-DIA method, we conduct extensive experiments on four benchmark datasets, including Hand Written2 [37], Caltech5V3 [38], Flower174 [39] and MSRCV15 [40]. |
| Dataset Splits | Yes | Specifically, assuming the missing ratio to be m, m percent of data samples are selected to remove at least one views randomly. In the following experiments, m is set in {0.1, 0.3, 0.5, 0.7.0.9}. |
| Hardware Specification | Yes | the codes of the proposed method and recent advances in comparison are executed on a server with 40 Intel(R) Xeon(R) Silver 4210R CPU @ 2.40GHz CPUs and 2 NVIDIA Ge Force RTX 3090 GPUs. |
| Software Dependencies | Yes | The software environment includes Python 3.10.13 and Py Torch 1.12.1 optimized with CUDA 11.4. |
| Experiment Setup | Yes | So does the proposed IMDC-DIA6 method with setting its only parameter β in {0.01, 0.1, 1, 10, 100}. Meanwhile, the unique data latent representation and parameters of neural netowrks are both optimized with gradient descent strategy with Adam optimizer whose learning rate is set to 0.001. In the experiments, we adopt fully-connected neural networks on all datasets where different numbers of neurons are adopted according to different feature dimensions, as shown in Table 4. |