Multidimensional Scaling

By S. Mancell, Clayton V. Deutsch. 2021

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Mathematical optimization in classification and regression trees (2021, background): “Extracting knowledge from data is a crucial task in Statistics and Machine Learning, and is at the core of many fields, such as Biomedicine (Jakaitiene et al. 2016; Pardalos et al. 2007); Business Analytics (Martens et al. 2007; Van Vlasselaer et al. 2017), Computational Optimization (Khalil et al.…”
Learning Metrics From Teachers: Compact Networks for Image Embedding (2019, methodology): “5 is equal to the loss used in the classical problem of multidimensional scaling (MDS) [7].”
Overview and comparative study of dimensionality reduction techniques for high dimensional data (2020, unknown): “MDS preserves an ideal pair wise distance in low dimensional space globally [196,197] .”
Multi-hop Federated Private Data Augmentation with Sample Compression (2019, background): “The configurated map displays the optimal distances among the converted points, which visualizes the level of similarity [Mair, 2018; Hout et al., 2016].”
Information-Geometric Dimensionality Reduction (2011, methodology): “Examples include principal component analysis (PCA), multidimensional scaling (MDS) [4], and ISOMAP [5].”
Machine Learning on Graphs: A Model and Comprehensive Taxonomy (2020, background): “In particular, metric MDS (mMDS) [44] minimizes the regularization loss in Eq.”
The sociality of personal and collective nostalgia (2019, methodology): “The ratings culminated in a participant-specific matrix, and these emotion comparison matrices were subjected to multidimensional scaling (Kruskal & Wish, 1978) in order to uncover dimensions of perceived similarity among the emotions.”
Deep learning for time series classification: a review (2018, methodology): “Figure 16 shows three MDS plots for the Wine dataset using: (1) the raw input time series (Figure 16a); (2) the learned latent features from the GAP layer for FCN (Figure 16b); and (3) the learned latent features from the GAP layer for ResNet (Figure 16c).”
Distance geometry and data science (2019, background): “The literature on multidimensional scaling (MDS) is extensive (Cox and Cox 2001; Borg and Groenen 2010), and many variants exist.”
AtSNE: Efficient and Robust Visualization on GPU through Hierarchical Optimization (2019, methodology): “Among all kinds of linear and non-linear dimension reduction methods [1, 9, 14, 17, 18], t-SNE [11] presents the best visual effect.”
GPU accelerated t-distributed stochastic neighbor embedding (2019, methodology): “A significant number of techniques have been proposed to do such dimensionality reduction with classical methods such as principal component analysis [13], [14], multi-dimensional scaling [15], and more modern methods such as Sammon mapping [16], curvilinear component analysis [17], stochastic neigh”
Big data and artificial intelligence in the maritime industry: a bibliometric review and future research directions (2020, methodology): “Although Bibliometrix offers a few alternatives, we used the multidimensional scaling (MDS) method (Cox and Cox 2000) for information visualisation and the Louvain clustering algorithm (Blondel et al. 2008) for detecting communities in networks.”
How to normalize cooccurrence data? An analysis of some well-known similarity measures (2009, unknown): “Outside the fields of scientometrics and information retrieval, the cosine is also known as the Ochiai coefficient (e.g., Cox and Cox, 2001, 2008; Hubálek, 1982; Sokal and Sneath, 1963).”
Metabolomics and Multi-Omics Integration: A Survey of Computational Methods and Resources (2020, background): “The input for MDS is a distance matrix representing pairwise distances between samples (or analytes) [58].”
Interaction of genotype, environment and processing in the chemical composition expression and sensorial quality of Arabica coffee (2016, background): “allows for the rearranging of the variable distribution in order to detect the smallest significant dimensions to explain their similarities or dissimilarities (Torgerson, 1952).”
Shift-invariant similarities circumvent distance concentration in stochastic neighbor embedding and variants (2011, methodology): “To provide comparison points, the results of Torgerson’s classical metric MDS [3] (CMMDS) and Demartines’ curvilinear component analysis [10] (CCA) are also shown.”