Related papers: Emerging-properties Mapping Using Spatial Embeddin…

Most Machine Learning (ML) methods, from clustering to classification, rely on a distance function to describe relationships between datapoints. For complex datasets it is hard to avoid making some arbitrary choices when defining a distance…

The aim of this research is to introduce a novel structural design process that allows architects and engineers to extend their typical design space horizon and thereby promoting the idea of creativity in structural design. The theoretical…

Existing approaches for graph neural networks commonly suffer from the oversmoothing issue, regardless of how neighborhoods are aggregated. Most methods also focus on transductive scenarios for fixed graphs, leading to poor generalization…

With the increasing availability of high-dimensional data, analysts often rely on exploratory data analysis to understand complex data sets. A key approach to exploring such data is dimensionality reduction, which embeds high-dimensional…

This article addresses extraction of physically meaningful information from STEM EELS and EDX spectrum-images using methods of Multivariate Statistical Analysis. The problem is interpreted in terms of data distribution in a…

Feature matching is a crucial task in the field of computer vision, which involves finding correspondences between images. Previous studies achieve remarkable performance using learning-based feature comparison. However, the pervasive…

Normalizing flows have shown great success as general-purpose density estimators. However, many real world applications require the use of domain-specific knowledge, which normalizing flows cannot readily incorporate. We propose…

We introduce an Expanded Parts Model (EPM) for recognizing human attributes (e.g. young, short hair, wearing suit) and actions (e.g. running, jumping) in still images. An EPM is a collection of part templates which are learnt…

Topological data analysis (TDA) is gaining prominence across a wide spectrum of machine learning tasks that spans from manifold learning to graph classification. A pivotal technique within TDA is persistent homology (PH), which furnishes an…

Industrial financial systems operate on temporal event sequences such as transactions, user actions, and system logs. While recent research emphasizes representation learning and large language models, production systems continue to rely…

Humans have the ability to regcognize the real world from different facets. Faceted exploration is a mechanism for browsing and understanding large-scale resources in information network by multiple facets. This paper proposes an Emerging…

In this study, we propose using a neural embedding model-graph neural network (GNN)- that leverages the heterogeneous features of urban areas and their interactions captured by human mobility network to obtain vector representations of…

Biological multimodal large language models (MLLMs) have emerged as powerful foundation models for scientific discovery. However, existing models are specialized to a single modality, limiting their ability to solve inherently cross-modal…

Predicting consumers' purchasing behaviors is critical for targeted advertisement and sales promotion in e-commerce. Human faces are an invaluable source of information for gaining insights into consumer personality and behavioral traits.…

The rapid increase in multimedia data has spurred advancements in Multimodal Summarization with Multimodal Output (MSMO), which aims to produce a multimodal summary that integrates both text and relevant images. The inherent heterogeneity…

The Expectation--Maximization (EM) algorithm is a simple meta-algorithm that has been used for many years as a methodology for statistical inference when there are missing measurements in the observed data or when the data is composed of…

Uniform Manifold Approximation and Projection (UMAP) is one of the state-of-the-art methods for dimensionality reduction and data visualization. This is a tutorial and survey paper on UMAP and its variants. We start with UMAP algorithm…

Single-cell sequencing is revolutionizing biology by enabling detailed investigations of cell-state transitions. Many biological processes unfold along continuous trajectories, yet it remains challenging to extract smooth, low-dimensional…

Human core object recognition depends on the selective use of visual information, but the strategies guiding these choices are difficult to measure directly. We present MAPS (Masked Attribution-based Probing of Strategies), a behaviorally…

As the proliferation of high-throughput approaches in materials science is increasing the wealth of data in the field, the gap between accumulated-information and derived-knowledge widens. We address the issue of scientific discovery in…