arXiv:2606. 04451v1 Announce Type: new Abstract: Neighbor embedding algorithms reveal correlations in high-dimensional data by constructing an equivalent graph representation in a lower-dimensional space.
arXiv:2607. 08746v1 Announce Type: cross Abstract: While UMAP is widely used for exploring high-dimensional data, typical workflows focus on its lower-dimensional embedding, largely overlooking the rich k-nearest-neighbor (kNN) graph that UMAP constructs internally.
arXiv:2605. 23540v2 Announce Type: replace Abstract: Dimensionality Reduction (DR) methods are widely used to visualize high-dimensional data.
arXiv:2509. 03373v2 Announce Type: replace Abstract: Dimensionality reduction methods such as t-SNE and UMAP are popular methods for visualizing data with a potential (latent) clustered structure.
The paper introduces a new image retrieval framework that merges neighbor embedding projections with rank-based manifold learning via rank aggregation. It uses UMAP to create low‑dimensional feature representations and combines ranked lists from UMAP and rank‑based re‑ranking methods using the Borda Count strategy. Experiments on public datasets with ResNet152, Swin Transformer, and DINOv2 features show that this combined approach improves retrieval performance, especially in scenarios where baseline representations have low precision.
arXiv:2601.20173v3 Announce Type: replace Abstract: We present a new nonlinear dimensionality reduction method, MAPLE, that enhances UMAP by improving manifold modeling. MAPLE employs a self-supervis...
The paper introduces the Rashomon set for dimension reduction, a collection of equally good embeddings that preserve high‑dimensional structure. It proposes PCA‑informed alignment to make axes interpretable, concept‑alignment regularization to incorporate external knowledge, and a method to extract trustworthy nearest‑neighbor relationships across the Rashomon set for refined embeddings. These techniques aim to produce interpretable, robust, and goal‑aligned visualizations by leveraging multiple valid embeddings instead of a single one.
arXiv:2605. 11428v2 Announce Type: replace Abstract: Exploratory analysis of high-dimensional data rarely stops at a single embedding.
arXiv:2608. 11269v1 Announce Type: cross Abstract: Omics datasets, particularly single-cell RNA sequencing data, are high-dimensional, sparse, noisy, and dominated by zero values, making faithful low-dimensional representation challenging.
The paper reviews methods for adding a new point to a vector diagram using proximity data, a problem first examined by J.C. Gower in 1968. It classifies existing kernel-based approaches into two strategies: projection, analogous to adding a point in principal component analysis, and restricted reconstruction, which seeks to re‑optimize the multivariate analysis while keeping the existing diagram fixed. The authors show that each method can be derived from one of these two strategies and discuss when each strategy may be preferable.
arXiv:2606. 02345v1 Announce Type: cross Abstract: Many machine learning problems, including similarity learning, ranking, and clustering, rely on empirical pairwise loss functions whose quadratic computational cost quickly becomes prohibitive at scale.
arXiv:2609.08152v1 Announce Type: new Abstract: Graph representation learning has largely focused on designing increasingly sophisticated models to transform graph topology into vector representation...
arXiv:2608.29001v1 Announce Type: new Abstract: In a data-driven world, efficiently organizing and mapping relationships between objects is crucial. Graphs are powerful tools for modeling these conne...