Uniform Manifold Approximation and Projection
PulseAugur coverage of Uniform Manifold Approximation and Projection — every cluster mentioning Uniform Manifold Approximation and Projection across labs, papers, and developer communities, ranked by signal.
- competes with t-Distributed Stochastic Neighbor Embedding 70%
- used by principal component analysis 70%
- used by hdbscan 60%
- instance of principal component analysis 60%
- used by Fashion-MNIST 60%
- instance of alphaXiv 60%
- instance of CatalyzeX 60%
- used by t-Distributed Stochastic Neighbor Embedding 50%
- competes with principal component analysis 50%
8 day(s) with sentiment data
-
New study explores self-supervised learning for binary program clustering
A new study explores the application of self-supervised learning (SSL) and tabular representation learning (TRL) for binary program clustering, a crucial task in cybersecurity for malware analysis. The research, conduct…
-
Graph Neural Networks Enhance Material Property Prediction for High-Entropy Oxides
Researchers have explored the use of graph neural networks (GNNs) for predicting the properties of high-entropy perovskite oxides (HEPOs), a complex class of materials. The study investigated ordered-to-disordered trans…
-
New DiRe framework enhances dimensionality reduction for global structure preservation
A new framework called DiRe has been developed for dimensionality reduction, aiming to preserve global structure and homological features. This method combines initial embedding with graph-based layout optimization and …
-
New FloDR method offers invertible dimensionality reduction with normalizing flows
Researchers have introduced FloDR, a novel invertible dimensionality reduction method that utilizes a normalizing flow. Unlike traditional methods like t-SNE and UMAP, which discard information during the optimization p…
-
Apple ML Research applies graph algorithms to UMAP's internal kNN graph
Apple Machine Learning Research has published a paper detailing how standard graph algorithms can be applied to the internal k-nearest-neighbor (kNN) graph constructed by Uniform Manifold Approximation and Projection (U…
-
B2B e-commerce transaction prediction framework improves precision with DiCE and PyPARC
A new paper introduces a framework for predicting transaction propensity in B2B e-commerce, addressing challenges posed by heterogeneous buyer behaviors that traditional methods like SMOTE struggle with. The proposed ap…
-
Unsupervised methods yield effective sentence embeddings for ancient languages
Researchers have developed two unsupervised learning strategies, TSDAE and contrastive sentence embedding (CSE), to create effective sentence embeddings for ancient languages. These methods adapt existing language model…
-
UMAP and DBSCAN enhance breast cancer data clustering from EHRs
Researchers have developed a new method for analyzing breast cancer data from electronic health records using unsupervised clustering. This approach combines Uniform Manifold Approximation and Projection (UMAP) for dime…
-
Paper warns of widespread misuse of t-SNE and UMAP in visual analytics
A new paper published on arXiv highlights the widespread misuse of dimensionality reduction techniques like t-SNE and UMAP in visual analytics. The research indicates that practitioners often misinterpret these tools, u…
-
Masked Autoencoder learns steel defect recognition with 91.3% accuracy
Researchers have developed a novel unsupervised method for recognizing steel surface defects using a Transformer-based Masked Autoencoder. This approach learns representations from abundant unlabeled images by masking 7…
-
New modular approach enhances data visualization transparency
Researchers have developed a new modular approach for data visualization that first clusters the data, then embeds each cluster individually, and finally aligns these clusters to create a global embedding. This method a…
-
New ML method NESS improves single-cell data analysis
Researchers have developed NESS, a new machine learning approach designed to improve the representation of single-cell data. This method builds upon the Predictability-Computability-Stability (PCS) framework to address …
-
UMAP's internal kNN graph unlocks new data analysis techniques
A new research paper explores the underutilized k-nearest-neighbor (kNN) graph generated internally by Uniform Manifold Approximation and Projection (UMAP). The study demonstrates how applying standard graph algorithms …
-
Unsupervised AI models can learn sensitive attributes, violating fairness
Researchers have demonstrated that unsupervised machine learning representations can inadvertently encode sensitive attributes like age and income, even when these attributes are excluded from the training data. A new m…
-
EntroPath: New manifold learning method uses path ensembles
Researchers have introduced EntroPath, a novel manifold learning method designed to reconstruct geodesic geometry from data graphs. This method utilizes ensembles of diffusion paths, specifically employing a maximum ent…
-
New unsupervised framework i-IF-Learn tackles high-dimensional data challenges
Researchers have developed i-IF-Learn, a novel unsupervised framework designed to tackle the challenges of high-dimensional data by simultaneously performing feature selection and clustering. This method identifies infl…
-
LLMs enhance software vulnerability categorization in new research
A new research paper explores the application of advanced topic modeling techniques, particularly those leveraging large language models (LLMs), for the categorization of software vulnerabilities. The study utilizes mod…
-
Study finds spectrum-like organization of states of mind in transformer representations
Researchers have investigated whether graded states of mind can be represented in a spectrum-like structure within transformer model representation spaces. They created a dataset of 636 sentences, each annotated with a …
-
FastUMAP offers scalable dimensionality reduction for exploratory data analysis
Researchers have developed FastUMAP, a novel method for scalable dimensionality reduction in high-dimensional data analysis. This landmark-based approach is designed for repeated use in exploratory analysis, offering a …
-
AI pipeline deciphers structural patterns in ancient Inka khipus
Researchers have developed a machine-learning pipeline to analyze Inka khipus, the knotted cord devices used by the Inka Empire for record-keeping. By engineering structural features from a database of 619 khipus, they …