Print Email Facebook Twitter Deep Recursive Embedding for High-Dimensional Data Title Deep Recursive Embedding for High-Dimensional Data Author Zhou, Zixia (Fudan University) Zu, Xinrui (University of Twente) Wang, Yuanyuan (Fudan University) Lelieveldt, Boudewijn P.F. (Universiteit Leiden) Tao, Q. (TU Delft ImPhys/Medical Imaging) Date 2021 Abstract Embedding high-dimensional data onto a low-dimensional manifold is of both theoretical and practical value. In this article, we propose to combine deep neural networks (DNN) with mathematics-guided embedding rules for high-dimensional data embedding. We introduce a generic deep embedding network (DEN) framework, which is able to learn a parametric mapping from high-dimensional space to low-dimensional space, guided by well-established objectives such as Kullback-Leibler (KL) divergence minimization. We further propose a recursive strategy, called deep recursive embedding (DRE), to make use of the latent data representations for boosted embedding performance. We exemplify the flexibility of DRE by different architectures and loss functions, and benchmarked our method against the two most popular embedding methods, namely, t-distributed stochastic neighbor embedding (t-SNE) and uniform manifold approximation and projection (UMAP). The proposed DRE method can map out-of-sample data and scale to extremely large datasets. Experiments on a range of public datasets demonstrated improved embedding performance in terms of local and global structure preservation, compared with other state-of-The-Art embedding methods. Code is available at https://github.com/tao-Aimi/DeepRecursiveEmbedding. Subject Data visualizationdeep embedding networkdeep recursive embeddingFeature extractionManifoldsStandardst-distributed stochastic neighbor embeddingToolsTraininguniform manifold approximation and projectionUnsupervised learningunsupervised learning To reference this document use: http://resolver.tudelft.nl/uuid:4c017a9f-22c8-49e7-8cdb-e737eb402b7e DOI https://doi.org/10.1109/TVCG.2021.3122388 ISSN 1077-2626 Source IEEE Transactions on Visualization and Computer Graphics, 28 (2), 1237-1248 Part of collection Institutional Repository Document type journal article Rights © 2021 Zixia Zhou, Xinrui Zu, Yuanyuan Wang, Boudewijn P.F. Lelieveldt, Q. Tao Files PDF Deep_Recursive_Embedding_ ... l_Data.pdf 3.44 MB Close viewer /islandora/object/uuid:4c017a9f-22c8-49e7-8cdb-e737eb402b7e/datastream/OBJ/view