.png){kind=icon}
返回
Layer-wise normalized deep incomplete multiview nonnegative matrix factorization
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2024.111010.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Deep (semi-)nonnegative matrix factorization based models have demonstrated promising performance in the multiview clustering tasks. However, they are all developed upon the assumption that the multiview datasets are complete in all views, and need to be pre-trained layer-by-layer to get reasonable results. Addressing these issues, an algorithm named layer-wise normalized deep incomplete multiview nonnegative matrix factorization (LWNdimNMF) is presented in this paper to tackle the multiview clustering problem with arbitrary missing views. Specifically, a novel layer-wise normalization strategy is developed to constrain the value distribution of the factor matrix in each layer to ensure the numerical stability of the model and make it robust to the initialization. Another benefit of this strategy is that it can effectively depress the objective function value and make the model fit data well. An instance selection alignment is adopted to fuse the incomplete multiple views by aligning the paired instances. To discover the high-order geometrical information in each incomplete view, a hypergraph regularization is incorporated into the proposed model. An effective iterative optimization algorithm based on the multiplicative updating rules is designed to solve the minimizing problem. Extensive experiments are conducted to evaluate the effectiveness of the proposed model by comparing with several state-of-the-art (SOTA) incomplete multiview clustering (IMC) methods on ten real-world multiview datasets. The source code is available at: https://github.com/GuoshengCui/LWNdimNMF.
Keyword:
Layer-wise normalization
Model stableness
Incomplete multiview clustering
Hypergraph regularization
期刊
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
Incomplete multi-modal representation learning for Alzheimer's disease diagnosis.png)
MEDICAL IMAGE ANALYSIS
MEDICAL IMAGE ANALYSISIF11.8
PREAI
分享收藏Joint Embedding Learning and Low-Rank Approximation: A Framework for Incomplete Multiview Learning
OAAI
OAAI分享收藏Weighted Sparse Graph Regularization for Spectral-Spatial Classification of Hyperspectral Images
PREAI
分享收藏View-aligned hypergraph learning for Alzheimer's disease diagnosis with incomplete multi-modality data视图对齐的超图学习用于不完整多模态数据的阿尔茨海默病诊断MEDICAL IMAGE ANALYSISOAAI
MEDICAL IMAGE ANALYSISIF11.8
OAAI分享收藏分享收藏
查看更多内容