Zhang Changqing, Geng Yu, Han Zongbo, Liu Yeqing, Fu Huazhu, Hu Qinghua
IEEE Trans Neural Netw Learn Syst. 2024 Feb;35(2):2263-2275. doi: 10.1109/TNNLS.2022.3189239. Epub 2024 Feb 5.
Modeling complex correlations on multiview data is still challenging, especially for high-dimensional features with possible noise. To address this issue, we propose a novel unsupervised multiview representation learning (UMRL) algorithm, termed autoencoder in autoencoder networks (AE2-Nets). The proposed framework effectively encodes information from high-dimensional heterogeneous data into a compact and informative representation with the proposed bidirectional encoding strategy. Specifically, the proposed AE2-Nets conduct encoding in two directions: the inner-AE-networks extract view-specific intrinsic information (forward encoding), while the outer-AE-networks integrate this view-specific intrinsic information from different views into a latent representation (backward encoding). For the nested architecture, we further provide a probabilistic explanation and extension from hierarchical variational autoencoder. The forward-backward strategy flexibly addresses high-dimensional (noisy) features within each view and encodes complementarity across multiple views in a unified framework. Extensive results on benchmark datasets validate the advantages compared to the state-of-the-art algorithms.
对多视图数据中的复杂相关性进行建模仍然具有挑战性，尤其是对于可能存在噪声的高维特征。为了解决这个问题，我们提出了一种新颖的无监督多视图表示学习（UMRL）算法，称为自动编码器网络中的自动编码器（AE2-Nets）。所提出的框架通过所提出的双向编码策略，有效地将来自高维异构数据的信息编码为紧凑且信息丰富的表示。具体而言，所提出的AE2-Nets在两个方向上进行编码：内部自动编码器网络提取特定视图的内在信息（正向编码），而外部自动编码器网络将来自不同视图的这种特定视图的内在信息集成到一个潜在表示中（反向编码）。对于嵌套架构，我们进一步从分层变分自动编码器提供了概率解释和扩展。前向-后向策略灵活地处理每个视图内的高维（有噪声）特征，并在统一框架中对多个视图之间的互补性进行编码。在基准数据集上的大量结果验证了与现有最先进算法相比的优势。
