Search

Classification tasks present challenges due to class imbalances and evolving data distributions. Addressing these issues requires a robust method to handle imbalances while effectively detecting out-of-distribution (OOD) samples not encountered during training. This study introduces a novel OOD detection algorithm designed for tabular datasets, titled Deep Neural Network-based Gaussian Descriptor for Imbalanced Tabular Data (DNN-GDITD). The DNN-GDITD algorithm can be placed on top of any DNN to facilitate better classification of imbalanced data and OOD detection using spherical decision boundaries. Using a combination of Push, Score-based, and focal losses, DNN-GDITD assigns confidence scores to test data points, categorizing them as known classes or as an OOD sample. Extensive experimentation on tabular datasets demonstrates the effectiveness of DNN-GDITD compared to three OOD algorithms. Evaluation encompasses imbalanced and balanced scenarios on diverse tabular datasets, including a synthetic financial dispute dataset and publicly available tabular datasets like Gas Sensor, Drive Diagnosis, and MNIST, showcasing DNN-GDITD's versatility., Comment: 17 pages

Thermoelectric devices that operate on quantum principles have been under extensive investigation in the past decades. These devices are at the fundamental limits of miniaturized heat engines and refrigerators, advancing the field of quantum thermodynamics. Most research in this area concerns the use of conduction electrons and holes as charge and heat carriers, and only very recently have superconductors been considered as thermal engines and thermoelectric devices. Here, we investigate the thermoelectric response of an Abrikosov vortex in type-II superconductors in the deep quantum limit. We consider two thermoelectric geometries, a type-II SIN junction and a local Scanning Tunneling Microscope (STM)-tip normal metal probe over the superconductor. We exploit the strong breaking of particle-hole symmetry in bound states at sub-gap energies within the superconducting vortex to realize a giant thermoelectric response in the presence of fluxons. We predict a thermovoltage of a few mV/K at sub-Kelvin temperatures using both semi-analytic and numerical self-consistent solutions of the Bogoliubov-de Gennes equations. Relevant thermoelectric coefficients and figures of merit are found within our model, both in linear and nonlinear regimes. The ZT of the SIN junction is around 1, rising to above 3 for the STM junction centered at the vortex core. We also discuss how this system can be used as a sensitive thermocouple, diode, or localized bolometer to detect low-energy single photons., Comment: 11 pages, 4 figures

Entity Alignment (EA) identifies entities across databases that refer to the same entity. Knowledge graph-based embedding methods have recently dominated EA techniques. Such methods map entities to a low-dimension space and align them based on their similarities. With the corpus of EA methodologies growing rapidly, this paper presents a comprehensive analysis of various existing EA methods, elaborating their applications and limitations. Further, we distinguish the methods based on their underlying algorithms and the information they incorporate to learn entity representations. Based on challenges in industrial datasets, we bring forward $4$ research questions (RQs). These RQs empirically analyse the algorithms from the perspective of \textit{Hubness, Degree distribution, Non-isomorphic neighbourhood,} and \textit{Name bias}. For Hubness, where one entity turns up as the nearest neighbour of many other entities, we define an $h$-score to quantify its effect on the performance of various algorithms. Additionally, we try to level the playing field for algorithms that rely primarily on name-bias existing in the benchmarking open-source datasets by creating a low name bias dataset. We further create an open-source repository for $14$ embedding-based EA methods and present the analysis for invoking further research motivations in the field of EA., Comment: 8 pages, 8 figures