In this paper, a number of data-driven solutions based on matrix and tensor decompositions are discussed, emphasizing how they account for diversity across the data sets, and a key concept, diversity, is introduced.
Abstract:
In various disciplines, information about the same phenomenon can be acquired from different types of detectors, at different conditions, in multiple experiments or subjects, among others. We use the term “modality” for each such acquisition framework. Due to the rich characteristics of natural phenomena, it is rare that a single modality provides complete knowledge of the phenomenon of interest. The increasing availability of several modalities reporting on the same system introduces new degrees of freedom, which raise questions beyond those related to exploiting each modality separately. As we argue, many of these questions, or “challenges,” are common to multiple domains. This paper deals with two key issues: “why we need data fusion” and “how we perform it.” The first issue is motivated by numerous examples in science and technology, followed by a mathematical framework that showcases some of the benefits that data fusion provides. In order to address the second issue, “diversity” is introduced as a key concept, and a number of data-driven solutions based on matrix and tensor decompositions are discussed, emphasizing how they account for diversity across the data sets. The aim of this paper is to provide the reader, regardless of his or her community of origin, with a taste of the vastness of the field, the prospects, and the opportunities that it holds.
TL;DR: The material covered includes tensor rank and rank decomposition; basic tensor factorization models and their relationships and properties; broad coverage of algorithms ranging from alternating optimization to stochastic gradient; statistical performance analysis; and applications ranging from source separation to collaborative filtering, mixture and topic modeling, classification, and multilinear subspace learning.
TL;DR: A thorough survey to fully understand Few-Shot Learning (FSL), and categorizes FSL methods from three perspectives: data, which uses prior knowledge to augment the supervised experience; model, which used to reduce the size of the hypothesis space; and algorithm, which using prior knowledgeto alter the search for the best hypothesis in the given hypothesis space.
TL;DR: This work first classify deep multimodal learning architectures and then discusses methods to fuse learned multi-modal representations in deep-learning architectures.
TL;DR: The aim of this paper is to provide the reader with a taste of the vastness of the field, the prospects, and the opportunities that it holds, and a number of data-driven solutions based on matrix and tensor decompositions are discussed, emphasizing how they account for diversity across the data sets.
TL;DR: Multi-view representation learning has become a rapidly growing direction in machine learning and data mining areas as mentioned in this paper, and a comprehensive survey of multi-view representations can be found in this paper.
TL;DR: In this article, the authors present results of both classic and recent matrix analyses using canonical forms as a unifying theme, and demonstrate their importance in a variety of applications, such as linear algebra and matrix theory.
TL;DR: This article reviews studies investigating complex brain networks in diverse experimental modalities and provides an accessible introduction to the basic principles of graph theory and highlights the technical challenges and key questions to be addressed by future developments in this rapidly moving field.
TL;DR: In this article, the distribution of the Mean Vector and the Covariance Matrix and the Generalized T2-Statistic is analyzed. But the distribution is not shown to be independent of sets of Variates.
Q1. What are the contributions mentioned in the paper "Multimodal data fusion: an overview of methods, challenges and prospects" ?
Due to the rich characteristics of natural phenomena, it is rare that a single modality provides complete knowledge of the phenomenon of interest. The increasing availability of several modalities reporting on the same system introduces new degrees of freedom, which raise questions beyond those related to exploiting each modality separately. This paper deals with two key questions: “ why the authors need data fusion ” and “ how they perform it ”. The first question is motivated by numerous examples in science and technology, followed by a mathematical framework that showcases some of the benefits that data fusion provides. In order to address the second question, “ diversity ” is introduced as a key concept, and a number of datadriven solutions based on matrix and tensor decompositions are discussed, emphasizing how they account for diversity across the datasets. The aim of this paper is to provide the reader, regardless of his or her community of origin, with a taste of the vastness of the field, the prospects and opportunities that it holds.
Q2. What other properties are often used to achieve uniqueness?
Other properties that are often used to achieve uniqueness, improve numerical robustness and enhance interpretability are, for example, non-negativity, sparsity, and smoothness [63].
Q3. What is the purpose of ongoing and planned sky surveys?
The purpose of ongoing and planned sky surveys is to decrease the allowable uncertainty volume of the six-dimensional ΛCDM parameter space and to improve the constraints on the other cosmological parameters that depend on it [51].
Q4. How does the Big Bang affect the evolution of the universe?
While CMB corresponds to photons released about 300,000 years after the Big Bang, the same parameters that controlled the evolution of the early Universe continue to influence its matter distribution and expansion rate to their very days.
Q5. What are some of the benefits of allowing more relaxed uniqueness conditions?
In particular, (i) allowing more relaxed uniqueness conditions that admit more challenging scenarios: for example, more relaxed assumptions on the underlying factors, and the ability to resolve more latent variables (low-rank terms) in each dataset, and (ii) terms that are shared across datasets enjoy the same permutation at all datasets.
Q6. What are the typical spatial resolutions of hyperspectral, multispectral and panchromatic?
Typical spatial resolutions of hyperspectral, multispectral and panchromatic images are tens of meters, a few meters and less than one meter, respectively.
Q7. What are the main reasons for linking datasets?
In both scenarios, the links themselves are new types of information: the fact that datasets are linked, that elements in different datasets are related (or not), and the nature of these interactions, bring new types of constraints into the system that allow to reduce the number of degrees of freedom and thus enhance uniqueness, performance, interpretability, and robustness, among others.
Q8. What type of constraint or assumption helps achieve essential uniqueness?
Any type of constraint or assumption on the underlying variables that helps achieve essential uniqueness can be regarded as a “diversity”.