Related papers: Disentangled Representation Learning for Astronomi…
Domain adaptation is an important but challenging task. Most of the existing domain adaptation methods struggle to extract the domain-invariant representation on the feature space with entangling domain information and semantic information.…
This study addresses the challenge of statistically extracting generative factors from complex, high-dimensional datasets in unsupervised or semi-supervised settings. We investigate encoder-decoder-based generative models for nonlinear…
From the intuitive notion of disentanglement, the image variations corresponding to different factors should be distinct from each other, and the disentangled representation should reflect those variations with separate dimensions. To…
Parametric system identification methods estimate the parameters of explicitly defined physical systems from data. Yet, they remain constrained by the need to provide an explicit function space, typically through a predefined library of…
Self-supervised representation learning often uses data augmentations to induce some invariance to "style" attributes of the data. However, with downstream tasks generally unknown at training time, it is difficult to deduce a priori which…
Dating stars is a major challenge with a deep impact on many astrophysical fields. One of the most promising techniques for this is using chemical abundances. Recent space- and ground-based facilities have improved the quantity of stars…
The first generation of large-scale chemical tagging surveys, in particular the HERMES/GALAH million star survey, promises to vastly expand our understanding of the chemical and dynamical evolution of the Galaxy. This, however, is…
Current autoencoder-based disentangled representation learning methods achieve disentanglement by penalizing the (aggregate) posterior to encourage statistical independence of the latent factors. This approach introduces a trade-off between…
The chemical makeup of a star provides the fossil information of the environment where it formed. Under this premise, it should be possible to use chemical abundances to tag stars that formed within the same stellar association. This idea -…
Representation learners that disentangle factors of variation have already proven to be important in addressing various real world concerns such as fairness and interpretability. Initially consisting of unsupervised models with independence…
The measurement of chemical abundances in planetary nebulae in nearby galaxies is now relatively straightforward. The challenge is to use these chemical abundances to infer the chemical evolution of their host galaxies. At this point, our…
Chemical evolution models are useful for understanding the formation and evolution of stars and galaxies. Model predictions will be more robust as more observational constraints are used. We present chemical evolution models for the dwarf…
Stellar evolution computations provide the foundation of several methods applied to study the evolutionary properties of stars and stellar populations, both Galactic and extragalactic. The accuracy of the results obtained with these…
Archetypal analysis represents each individual member of a set of data vectors as a mixture (a constrained linear combination) of the pure types or archetypes of the data set. The archetypes are themselves required to be mixtures of the…
Multi-view representation learning aims to derive robust representations that are both view-consistent and view-specific from diverse data sources. This paper presents an in-depth analysis of existing approaches in this domain, highlighting…
According to density functional theory, any chemical property can be inferred from the electron density, making it the most informative attribute of an atomic structure. In this work, we demonstrate the use of established physical methods…
Stellar ages are key for determining the formation history of the Milky Way, but are difficult to measure precisely. Furthermore, methods that use chemical abundances to infer ages may entangle the intrinsic evolution of stars with the…
Despite extensive standardization, diagnostic interviews for mental health disorders encompass substantial subjective judgment. Previous studies have demonstrated that EEG-based neural measures can function as reliable objective correlates…
Spectral methods have emerged as a simple yet surprisingly effective approach for extracting information from massive, noisy and incomplete data. In a nutshell, spectral methods refer to a collection of algorithms built upon the eigenvalues…
In this paper we emphasize the close connection between the chemical and spectrophotometric evolution of stellar systems: Chemical yields from stars correspond to a precise fraction of their emitted light. We translate this concept…