UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction

Abstract

UMAP (Uniform Manifold Approximation and Projection) is a novel manifold learning technique for dimension reduction. UMAP is constructed from a theoretical framework based in Riemannian geometry and algebraic topology. The result is a practical scalable algorithm that applies to real world data. The UMAP algorithm is competitive with t-SNE for visualization quality, and arguably preserves more of the global structure with superior run time performance. Furthermore, UMAP has no computational restrictions on embedding dimension, making it viable as a general purpose dimension reduction technique for machine learning.

arXiv commentReference implementation available at http://github.com/lmcinnes/umap

References in corpus (7)

• Distributed Representations of Words and Phrases and their Compositionality
• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• A Survey on Metric Learning for Feature Vectors and Structured Data
• Manifold Learning of Four-dimensional Scanning Transmission Electron Microscopy
• Data-Driven Design: Exploring new Structural Forms using Machine Learning and Graphic Statics
• (Self-Attentive) Autoencoder-based Universal Language Representation for Machine Translation
• Gaussian mixture models with Wasserstein distance

Cited by in corpus (545)

• COVID-19 Image Data Collection: Prospective Predictions Are the Future
• Combining Machine Learning and Computational Chemistry for Predictive Insights Into Chemical Systems
• Principal Component Analysis: A Natural Approach to Data Exploration
• E-GraphSAGE: A Graph Neural Network based Intrusion Detection System for IoT
• Self-attention for raw optical Satellite Time Series Classification
• Accelerating high-throughput virtual screening through molecular pool-based active learning
• Neural population geometry: An approach for understanding biological and artificial neural networks
• polyBERT: A chemical language model to enable fully machine-driven ultrafast polymer informatics
• Deep Representation Learning of Patient Data from Electronic Health Records (EHR): A Systematic Review
• Understanding How Dimension Reduction Tools Work: An Empirical Approach to Deciphering t-SNE, UMAP, TriMAP, and PaCMAP for Data Visualization
• Explainable Artificial Intelligence: A Survey of Needs, Techniques, Applications, and Future Direction
• Designing Interpretable ML System to Enhance Trust in Healthcare: A Systematic Review to Proposed Responsible Clinician-AI-Collaboration Framework
• TITAN: T Cell Receptor Specificity Prediction with Bimodal Attention Networks
• A Neural Network Solves, Explains, and Generates University Math Problems by Program Synthesis and Few-Shot Learning at Human Level
• Initial recommendations for performing, benchmarking, and reporting single-cell proteomics experiments
• Visualizing and Measuring the Geometry of BERT
• Latent ODEs for Irregularly-Sampled Time Series
• StackGenVis: Alignment of Data, Algorithms, and Models for Stacking Ensemble Learning Using Performance Metrics
• A Survey on Device Behavior Fingerprinting: Data Sources, Techniques, Application Scenarios, and Datasets
• Machine Learning in Astronomy: a practical overview
• OmiEmbed: a unified multi-task deep learning framework for multi-omics data
• Anti-Money Laundering in Bitcoin: Experimenting with Graph Convolutional Networks for Financial Forensics
• Supporting Analysis of Dimensionality Reduction Results with Contrastive Learning
• Capsule Attention for Multimodal EEG-EOG Representation Learning with Application to Driver Vigilance Estimation
• Knowledge Graph informed Fake News Classification via Heterogeneous Representation Ensembles
• Contrast to Divide: Self-Supervised Pre-Training for Learning with Noisy Labels
• Robust And Scalable Learning Of Complex Dataset Topologies Via Elpigraph
• Integrated Multi-omics Analysis Using Variational Autoencoders: Application to Pan-cancer Classification
• Revisiting Dimensionality Reduction Techniques for Visual Cluster Analysis: An Empirical Study
• Self-Supervised Representation Learning for Astronomical Images
• Analysis and visualization of spatial transcriptomic data
• Catalogue of new Herbig Ae/Be and classical Be stars. A machine learning approach to Gaia DR2
• Feature Robustness in Non-stationary Health Records: Caveats to Deployable Model Performance in Common Clinical Machine Learning Tasks
• Measuring and modeling the motor system with machine learning
• Forecasting Covid-19 dynamics in Brazil: a data driven approach
• Causal Network Models of SARS-CoV-2 Expression and Aging to Identify Candidates for Drug Repurposing
• A Similarity Measure for Material Appearance
• Manifold Learning of Four-dimensional Scanning Transmission Electron Microscopy
• Ranking the information content of distance measures
• The Limitations of Adversarial Training and the Blind-Spot Attack
• Alert Classification for the ALeRCE Broker System: The Real-time Stamp Classifier
• Bioplastic Design using Multitask Deep Neural Networks
• A Survey of Deep Learning for Scientific Discovery
• Putting Density Functional Theory to the Test in Machine-Learning-Accelerated Materials Discovery
• Foundations of Population-Based SHM, Part IV: The Geometry of Spaces of Structures and their Feature Spaces
• Genetic Programming for Evolving a Front of Interpretable Models for Data Visualisation
• Target specific mining of COVID-19 scholarly articles using one-class approach
• Interactive Dimensionality Reduction for Comparative Analysis
• Uncloaking hidden repeating fast radio bursts with unsupervised machine learning
• Kartezio: Evolutionary Design of Explainable Pipelines for Biomedical Image Analysis
• Assessing deep learning methods for the identification of kidney stones in endoscopic images
• Learning identifiable and interpretable latent models of high-dimensional neural activity using pi-VAE
• Scalability in Visualization
• EXACT: A collaboration toolset for algorithm-aided annotation of images with annotation version control
• Learning physical properties of anomalous random walks using graph neural networks
• Unsupervised classification to improve the quality of a bird song recording dataset
• Database, Features, and Machine Learning Model to Identify Thermally Driven Metal-Insulator Transition Compounds
• A review of unsupervised learning in astronomy
• Entangled Watermarks as a Defense against Model Extraction
• Multiscale reweighted stochastic embedding (MRSE): Deep learning of collective variables for enhanced sampling
• Large image datasets: A pyrrhic win for computer vision?
• Adaptive 3D descattering with a dynamic synthesis network
• Solo-learn: A Library of Self-supervised Methods for Visual Representation Learning
• Machine learning for assessing quality of service in the hospitality sector based on customer reviews
• Deep Learning Criminal Networks
• pyBibX -- A Python Library for Bibliometric and Scientometric Analysis Powered with Artificial Intelligence Tools
• Wikipedia2Vec: An Efficient Toolkit for Learning and Visualizing the Embeddings of Words and Entities from Wikipedia
• Interpretable machine learning for inferring the phase boundaries in a nonequilibrium system
• Semi-Automatic Data Annotation guided by Feature Space Projection
• Machine learning of microstructure--property relationships in materials leveraging microstructure representation from foundational vision transformers
• Using Language Model to Bootstrap Human Activity Recognition Ambient Sensors Based in Smart Homes
• Topological Persistence Machine of Phase Transitions
• Phase diagram study of a two-dimensional frustrated antiferromagnet via unsupervised machine learning
• Hierarchical Disentanglement-Alignment Network for Robust SAR Vehicle Recognition
• Sociotechnical Audits: Broadening the Algorithm Auditing Lens to Investigate Targeted Advertising
• Multi-domain stain normalization for digital pathology: A cycle-consistent adversarial network for whole slide images
• TorchXRayVision: A library of chest X-ray datasets and models
• Visualizing probabilistic models: Intensive Principal Component Analysis
• Interpretability of a Deep Learning Model in the Application of Cardiac MRI Segmentation with an ACDC Challenge Dataset
• Uniform Manifold Approximation and Projection (UMAP) and its Variants: Tutorial and Survey
• Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentation
• Unsupervised machine learning for transient discovery in Deeper, Wider, Faster light curves
• Top2Vec: Distributed Representations of Topics
• Domain Adaptation for Robust Workload Level Alignment Between Sessions and Subjects using fNIRS
• Fisher Discriminant Triplet and Contrastive Losses for Training Siamese Networks
• Measuring and Explaining the Inter-Cluster Reliability of Multidimensional Projections
• Machine learning approach to genome of two-dimensional materials with flat electronic bands
• Projection pursuit adaptation on polynomial chaos expansions
• Design Space Exploration and Explanation via Conditional Variational Autoencoders in Meta-model-based Conceptual Design of Pedestrian Bridges
• Self-Supervised Deep Learning on Point Clouds by Reconstructing Space
• Federated Principal Component Analysis
• Self-Supervised Similarity Learning for Digital Pathology
• CPR: Classifier-Projection Regularization for Continual Learning
• Unsupervised learning of atomic environments from simple features
• Unbiased organism-agnostic and highly sensitive signal peptide predictor with deep protein language model
• Strong and weak principles of neural dimension reduction
• Hyper-SAGNN: a self-attention based graph neural network for hypergraphs
• A Survey on Contextualised Semantic Shift Detection
• Visualizing Data using GTSNE
• TriMap: Large-scale Dimensionality Reduction Using Triplets
• DeepVATS: Deep Visual Analytics for Time Series
• A deep learning approach to clustering visual arts
• WaveNet-Based Deep Neural Networks for the Characterization of Anomalous Diffusion (WADNet)
• Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement Learning
• Understanding Aesthetic Evaluation using Deep Learning
• Evaluating the Underlying Gender Bias in Contextualized Word Embeddings
• Universal Detection of Backdoor Attacks via Density-based Clustering and Centroids Analysis
• VisEvol: Visual Analytics to Support Hyperparameter Search through Evolutionary Optimization
• ConceptEVA: Concept-Based Interactive Exploration and Customization of Document Summaries
• LAEO-Net++: revisiting people Looking At Each Other in videos
• An Interpretable Machine Learning Model for Deformation of Multi-Walled Carbon Nanotubes
• Hunting for C-rich long-period variable stars in the Milky Way's bar-bulge using unsupervised classification of Gaia BP/RP spectra
• Parallel locomotor control strategies in mice and flies
• Topological Data Analysis in smart manufacturing: State of the art and futuredirections
• RP2K: A Large-Scale Retail Product Dataset for Fine-Grained Image Classification
• iART: A Search Engine for Art-Historical Images to Support Research in the Humanities
• Learn molecular representations from large-scale unlabeled molecules for drug discovery
• CLIMATE-FEVER: A Dataset for Verification of Real-World Climate Claims
• A catalogue of 323 cataclysmic variables from LAMOST DR6
• Extracting the main trend in a dataset: the Sequencer algorithm
• CosSIF: Cosine similarity-based image filtering to overcome low inter-class variation in synthetic medical image datasets
• Capturing the physics of MaNGA galaxies with self-supervised Machine Learning
• WESPER: Zero-shot and Realtime Whisper to Normal Voice Conversion for Whisper-based Speech Interactions
• Analysing Deep Reinforcement Learning Agents Trained with Domain Randomisation
• A semi-supervised Machine Learning search for never-seen Gravitational-Wave sources
• Generating semantic maps through multidimensional scaling: linguistic applications and theory
• Generating Similarity Map for COVID-19 Transmission Dynamics with Topological Autoencoder
• Recurrent Quantum Neural Networks
• Visualizing Graph Neural Networks with CorGIE: Corresponding a Graph to Its Embedding
• Uniform Manifold Approximation with Two-phase Optimization
• Extendable and invertible manifold learning with geometry regularized autoencoders
• Visualising energy landscapes through manifold learning
• Self-supervised EEG Representation Learning for Automatic Sleep Staging
• The Elements of Visual Art Recommendation: Learning Latent Semantic Representations of Paintings
• Faster and more diverse de novo molecular optimization with double-loop reinforcement learning using augmented SMILES
• Angler: Helping Machine Translation Practitioners Prioritize Model Improvements
• When Explainability Meets Adversarial Learning: Detecting Adversarial Examples using SHAP Signatures
• Claim Detection for Automated Fact-checking: A Survey on Monolingual, Multilingual and Cross-Lingual Research
• Text and Style Conditioned GAN for Generation of Offline Handwriting Lines
• Towards better Interpretable and Generalizable AD detection using Collective Artificial Intelligence
• Representation Learning for Electronic Health Records
• CommonsenseVIS: Visualizing and Understanding Commonsense Reasoning Capabilities of Natural Language Models
• Evaluation of Similarity-based Explanations
• Forest Fire Clustering for Single-cell Sequencing with Iterative Label Propagation and Parallelized Monte Carlo Simulation
• Secuer: ultrafast, scalable and accurate clustering of single-cell RNA-seq data
• Manifold Learning in Atomistic Simulations: A Conceptual Review
• Inorganic synthesis-structure maps in zeolites with machine learning and crystallographic distances
• Why do Angular Margin Losses work well for Semi-Supervised Anomalous Sound Detection?
• Astronomaly at scale: searching for anomalies amongst 4 million galaxies
• GPT-assisted learning of structure-property relationships by graph neural networks: Application to rare-earth doped phosphors
• Mixing autoencoder with classifier: conceptual data visualization
• Coverage Hole Detection for mmWave Networks: An Unsupervised Learning Approach
• Fine-Grained Prediction of Political Leaning on Social Media with Unsupervised Deep Learning
• VideoPro: A Visual Analytics Approach for Interactive Video Programming
• Enabling Unsupervised Discovery in Astronomical Images through Self-Supervised Representations
• PTransIPs: Identification of phosphorylation sites enhanced by protein PLM embeddings
• MIC: Mining Interclass Characteristics for Improved Metric Learning
• An Unsupervised Framework for Comparing Graph Embeddings
• VisRuler: Visual Analytics for Extracting Decision Rules from Bagged and Boosted Decision Trees
• SCLAiR : Supervised Contrastive Learning for User and Device Independent Airwriting Recognition
• Controlled Analyses of Social Biases in Wikipedia Bios
• BatmanNet: Bi-branch Masked Graph Transformer Autoencoder for Molecular Representation
• Reconsidering the dynamical states of galaxy clusters using PCA and UMAP
• On UMAP's true loss function
• Child-Computer Interaction with Mobile Devices: Recent Works, New Dataset, and Age Detection
• Pattern Matching and Classification of Clusters in Collision Cascades
• Escaping the curse of dimensionality in Bayesian model based clustering
• Multimodal machine learning with large language embedding model for polymer property prediction
• Synthesizing Event-centric Knowledge Graphs of Daily Activities Using Virtual Space
• Projected $t$-SNE for batch correction
• #PraCegoVer: A Large Dataset for Image Captioning in Portuguese
• The Missing Path: Analysing Incompleteness in Knowledge Graphs
• Multiscale entropy analysis of astronomical time series. Discovering subclusters of hybrid pulsators
• UMat: Uncertainty-Aware Single Image High Resolution Material Capture
• Modeling User Behavior With Interaction Networks for Spam Detection
• GCExplainer: Human-in-the-Loop Concept-based Explanations for Graph Neural Networks
• Nonlinear Dimensionality Reduction for Data Visualization: An Unsupervised Fuzzy Rule-based Approach
• The Impact of Racial Distribution in Training Data on Face Recognition Bias: A Closer Look
• Detecting Financial Bots on the Ethereum Blockchain
• The Language Interpretability Tool: Extensible, Interactive Visualizations and Analysis for NLP Models
• Gradual Domain Adaptation without Indexed Intermediate Domains
• Under the Hood of Neural Networks: Characterizing Learned Representations by Functional Neuron Populations and Network Ablations
• Generalizing Hate Speech Detection Using Multi-Task Learning: A Case Study of Political Public Figures
• A biology-driven deep generative model for cell-type annotation in cytometry
• Novelty Detection and Analysis of Traffic Scenario Infrastructures in the Latent Space of a Vision Transformer-Based Triplet Autoencoder
• Exploring the evolution of research topics during the COVID-19 pandemic
• HUMAP: Hierarchical Uniform Manifold Approximation and Projection
• Rethinking Architecture Design for Tackling Data Heterogeneity in Federated Learning
• Investigation of Self-supervised Pre-trained Models for Classification of Voice Quality from Speech and Neck Surface Accelerometer Signals
• Exploring UMAP in hybrid models of entropy-based and representativeness sampling for active learning in biomedical segmentation
• Expert-LaSTS: Expert-Knowledge Guided Latent Space for Traffic Scenarios
• DeepSI: Interactive Deep Learning for Semantic Interaction
• Conditional out-of-sample generation for unpaired data using trVAE
• Force-Directed Graph Layouts Revisited: A New Force Based on the T-Distribution
• Wide Area VISTA Extra-galactic Survey (WAVES): Unsupervised star-galaxy separation on the WAVES-Wide photometric input catalogue using UMAP and $\mathrm{HDBSCAN}$
• Large-Scale Evaluation of Topic Models and Dimensionality Reduction Methods for 2D Text Spatialization
• Unsupervised KPIs-Based Clustering of Jobs in HPC Data Centers
• Modeling PROTAC Degradation Activity with Machine Learning
• Interpreting core forms of urban morphology linked to urban functions with explainable graph neural network
• Pairwise Supervised Hashing with Bernoulli Variational Auto-Encoder and Self-Control Gradient Estimator
• Data clustering: a fundamental method in data science and management
• Metadata augmented deep neural networks for wild animal classification
• The blame game: Understanding blame assignment in social media
• ExplorerTree: a focus+context exploration approach for 2D embeddings
• Reconstructing Three-decade Global Fine-Grained Nighttime Light Observations by a New Super-Resolution Framework
• Global Wheat Head Dataset 2021: more diversity to improve the benchmarking of wheat head localization methods
• Detecting Social Media Manipulation in Low-Resource Languages
• Neural Embeddings of Urban Big Data Reveal Emergent Structures in Cities
• Entanglement: Cybercrime Connections of an Internet Marketing Forum Population
• SUBPLEX: Towards a Better Understanding of Black Box Model Explanations at the Subpopulation Level
• A Riemannian Stochastic Representation for Quantifying Model Uncertainties in Molecular Dynamics Simulations
• SPROUT: an Interactive Authoring Tool for Generating Programming Tutorials with the Visualization of Large Language Models
• Identification of Rare Cortical Folding Patterns using Unsupervised Deep Learning
• Contrastive Prototype Learning with Augmented Embeddings for Few-Shot Learning
• Multi-modal machine learning analysis of GaSe molecular beam epitaxy growth conditions
• Zero-Shot Paragraph-level Handwriting Imitation with Latent Diffusion Models
• VAINE: Visualization and AI for Natural Experiments
• One4all User Representation for Recommender Systems in E-commerce
• (Self-Attentive) Autoencoder-based Universal Language Representation for Machine Translation
• Now You See It, Now You Dont: Adversarial Vulnerabilities in Computational Pathology
• Subspace Clustering using Ensembles of $K$-Subspaces
• Improving Transferability of Domain Adaptation Networks Through Domain Alignment Layers
• Expert Decision Support System for aeroacoustic source type identification using clustering
• Bidirectional GaitNet: A Bidirectional Prediction Model of Human Gait and Anatomical Conditions
• Category Theory in Machine Learning
• baller2vec: A Multi-Entity Transformer For Multi-Agent Spatiotemporal Modeling
• Incorporating Texture Information into Dimensionality Reduction for High-Dimensional Images
• Beyond Imitation: Generative and Variational Choreography via Machine Learning
• Supervised Dimensionality Reduction and Visualization using Centroid-encoder
• CuratorNet: Visually-aware Recommendation of Art Images
• Self-supervised edge features for improved Graph Neural Network training
• Semi-supervised on-device neural network adaptation for remote and portable laser-induced breakdown spectroscopy
• Trusted Artificial Intelligence: Towards Certification of Machine Learning Applications
• Mixed Multi-Model Semantic Interaction for Graph-based Narrative Visualizations
• Surprise machines: revealing Harvard Art Museums' image collection
• Positive and unlabelled machine learning reveals new fast radio burst repeater candidates
• Estimating Photometric Redshifts for Galaxies from the DESI Legacy Imaging Surveys with Bayesian Neural Networks Trained by DESI EDR
• Learning to rumble: Automated elephant call classification, detection and endpointing using deep architectures
• Coarse-grained crystal graph neural networks for reticular materials design
• Multi-center anatomical segmentation with heterogeneous labels via landmark-based models
• MEAL: Manifold Embedding-based Active Learning
• LDLE: Low Distortion Local Eigenmaps
• Factorized Discriminant Analysis for Genetic Signatures of Neuronal Phenotypes
• Fairest of Them All: Establishing a Strong Baseline for Cross-Domain Person ReID
• Gaussian mixture models with Wasserstein distance
• Focusing on Potential Named Entities During Active Label Acquisition
• Classifying the classifier: dissecting the weight space of neural networks
• The Categorical Data Map: A Multidimensional Scaling-Based Approach
• Causal Imputation via Synthetic Interventions
• Voice Cloning: a Multi-Speaker Text-to-Speech Synthesis Approach based on Transfer Learning
• Lack of evidence for correlation between COVID-19 infodemic and vaccine acceptance
• Neural Network Embeddings for Test Case Prioritization
• A journey in ESN and LSTM visualisations on a language task
• Clinically Relevant Latent Space Embedding of Cancer Histopathology Slides through Variational Autoencoder Based Image Compression
• ActiLabel: A Combinatorial Transfer Learning Framework for Activity Recognition
• Emo-DNA: Emotion Decoupling and Alignment Learning for Cross-Corpus Speech Emotion Recognition
• Two-by-two ordinal patterns in art paintings
• Narrative Maps: An Algorithmic Approach to Represent and Extract Information Narratives
• InstaNAS: Instance-aware Neural Architecture Search
• ChildCI Framework: Analysis of Motor and Cognitive Development in Children-Computer Interaction for Age Detection
• DEUCE: Dual-diversity Enhancement and Uncertainty-awareness for Cold-start Active Learning
• Learning Trailer Moments in Full-Length Movies
• Site-Specific Ground Motion Generative Model for Crustal Earthquakes in Japan Based on Generative Adversarial Networks
• Domain Adversarial RetinaNet as a Reference Algorithm for the MItosis DOmain Generalization Challenge
• Unsupervised Deep Manifold Attributed Graph Embedding
• Deciphering quantum fingerprints in electric conductance
• Projective Latent Interventions for Understanding and Fine-tuning Classifiers
• Quantile-Quantile Embedding for Distribution Transformation and Manifold Embedding with Ability to Choose the Embedding Distribution
• Learning a low dimensional manifold of real cancer tissue with PathologyGAN
• SemanticAxis: Exploring Multi-attribute Data by Semantics Construction and Ranking Analysis
• Markov-Lipschitz Deep Learning
• A News-based Machine Learning Model for Adaptive Asset Pricing
• Exploring Public Attention in the Circular Economy through Topic Modelling with Twin Hyperparameter Optimisation
• DeepBeat: A multi-task deep learning approach to assess signal quality and arrhythmia detection in wearable devices
• Consistent Representation Learning for High Dimensional Data Analysis
• Query by Semantic Sketch
• GRB 241105A: A test case for GRB classification and rapid r-process nucleosynthesis channels
• Towards an Automated Pipeline for Detecting and Classifying Malware through Machine Learning
• Visual Ensemble Analysis of Fluid Flow in Porous Media across Simulation Codes and Experiment
• Learning from Imperfect Annotations
• Event detection in Colombian security Twitter news using fine-grained latent topic analysis
• Correlation of Auroral Dynamics and GNSS Scintillation with an Autoencoder
• Advancing the Biological Plausibility and Efficacy of Hebbian Convolutional Neural Networks
• Galaxy Manifold: Characterizing and understanding galaxies with two parameters
• Casting Multiple Shadows: High-Dimensional Interactive Data Visualisation with Tours and Embeddings
• Spatial LibriSpeech: An Augmented Dataset for Spatial Audio Learning
• Emotion Embedding Spaces for Matching Music to Stories
• Multi-Stage Prototype Learning for Interpretable Time Series Classification
• BarcodeBERT: Transformers for Biodiversity Analysis
• Applying machine learning to Galactic Archaeology: how well can we recover the origin of stars in Milky Way-like galaxies?
• Fuzzy sets and presheaves
• SQRQuerier: A Visual Querying Framework for Cross-national Survey Data Recycling
• Distributed generation of privacy preserving data with user customization
• TickIt: Leveraging Large Language Models for Automated Ticket Escalation
• Bringing manifold learning and dimensionality reduction to SED fitters
• Exploring the Impact of Corpus Diversity on Financial Pretrained Language Models
• A Deep Learning Approach to Private Data Sharing of Medical Images Using Conditional GANs
• Selecting the independent coordinates of manifolds with large aspect ratios
• Counterfactual Explanations of Concept Drift
• Learning to Taste: A Multimodal Wine Dataset
• Estimating cellular redundancy in networks of genetic expression
• Isometric Gaussian Process Latent Variable Model for Dissimilarity Data
• Revisiting IPA-based Cross-lingual Text-to-speech
• A Probabilistic Graph Coupling View of Dimension Reduction
• CSI Clustering with Variational Autoencoding
• Explaining classifiers to understand coarse-grained models
• T-SNE Is Not Optimized to Reveal Clusters in Data
• Conditional t-SNE: Complementary t-SNE embeddings through factoring out prior information
• Supervised Representation Learning towards Generalizable Assembly State Recognition
• Deep Generative Models Strike Back! Improving Understanding and Evaluation in Light of Unmet Expectations for OoD Data
• Unsupervised Representation Learning by Predicting Random Distances
• Neural networks for boosted di-$\tau$ identification
• Learning Malware Representation based on Execution Sequences
• Wearable data from subjects playing Super Mario, sitting university exams, or performing physical exercise help detect acute mood episodes via self-supervised learning
• Local Concept Embeddings for Analysis of Concept Distributions in Vision DNN Feature Spaces
• Wider Networks Learn Better Features
• No Regret Sample Selection with Noisy Labels
• Zero-shot and few-shot time series forecasting with ordinal regression recurrent neural networks
• Stock2Vec: A Hybrid Deep Learning Framework for Stock Market Prediction with Representation Learning and Temporal Convolutional Network
• Drug-Drug Interaction Prediction with Wasserstein Adversarial Autoencoder-based Knowledge Graph Embeddings
• Manifold Learning via Manifold Deflation
• E3-targetPred: Prediction of E3-Target Proteins Using Deep Latent Space Encoding
• ScatterUQ: Interactive Uncertainty Visualizations for Multiclass Deep Learning Problems
• A Subspace-based Approach for Dimensionality Reduction and Important Variable Selection
• Atomic-scale analysis of disorder by similarity learning from tunneling spectroscopy
• XInsight: Revealing Model Insights for GNNs with Flow-based Explanations
• PeopleMap: Visualization Tool for Mapping Out Researchers using Natural Language Processing
• From Theory to Behaviour: Towards a General Model of Engagement
• A Distance-preserving Matrix Sketch
• Deep Manifold Transformation for Nonlinear Dimensionality Reduction
• Local Two-Sample Testing over Graphs and Point-Clouds by Random-Walk Distributions
• Situated Case Studies for a Human-Centered Design of Explanation User Interfaces
• Topic Modeling in the Voynich Manuscript
• Neural-adjoint method for the inverse design of all-dielectric metasurfaces
• Global Wheat Challenge 2020: Analysis of the competition design and winning models
• Wavelength Dependence of Image Quality Metrics and Seeing Parameters and their Relation to Adaptive Optics Performance
• A Wasserstein Graph Distance Based on Distributions of Probabilistic Node Embeddings
• How Deep Is Your Gaze? Leveraging Distance in Image-Based Gaze Analysis
• Unveiling 3D Ocean Biogeochemical Provinces in the North Atlantic: A Systematic Comparison and Validation of Clustering Methods
• The Unreasonable Effectiveness of Large Language-Vision Models for Source-free Video Domain Adaptation
• Sedition Hunters: A Quantitative Study of the Crowdsourced Investigation into the 2021 U.S. Capitol Attack
• Investigating Privacy Leakage in Dimensionality Reduction Methods via Reconstruction Attack
• FLASC: A Flare-Sensitive Clustering Algorithm
• Analysing State-Backed Propaganda Websites: a New Dataset and Linguistic Study
• T-Rep: Representation Learning for Time Series using Time-Embeddings
• A dataset of mentorship in science with semantic and demographic estimations
• Overhead-MNIST: Machine Learning Baselines for Image Classification
• An Analytical Survey on Recent Trends in High Dimensional Data Visualization
• Stochastic Cluster Embedding
• Assessing glaucoma in retinal fundus photographs using Deep Feature Consistent Variational Autoencoders
• Self-supervised Feature-Gate Coupling for Dynamic Network Pruning
• MAD-VAE: Manifold Awareness Defense Variational Autoencoder
• Clustering with UMAP: Why and How Connectivity Matters
• VisBERT: Hidden-State Visualizations for Transformers
• Local Latent Representation based on Geometric Convolution for Particle Data Feature Exploration
• Sketch and Scale: Geo-distributed tSNE and UMAP
• Accounting for Affect in Pain Level Recognition
• Generating private data with user customization
• Metric spaces and homotopy types
• Learning disentangled representations via product manifold projection
• Unsupervised Functional Data Analysis via Nonlinear Dimension Reduction
• VERB: Visualizing and Interpreting Bias Mitigation Techniques for Word Representations
• Feature Selection Using Batch-Wise Attenuation and Feature Mask Normalization
• KNN-DBSCAN: a DBSCAN in high dimensions
• A Few Topical Tweets are Enough for Effective User-Level Stance Detection
• Batch-Incremental Triplet Sampling for Training Triplet Networks Using Bayesian Updating Theorem
• Instance Selection for GANs
• Manifold structure in graph embeddings
• Self-similarity Student for Partial Label Histopathology Image Segmentation
• SMAP: A Joint Dimensionality Reduction Scheme for Secure Multi-Party Visualization
• Practical Cross-modal Manifold Alignment for Grounded Language
• A Set of Distinct Facial Traits Learned by Machines Is Not Predictive of Appearance Bias in the Wild
• TopoAct: Visually Exploring the Shape of Activations in Deep Learning
• FastEstimator: A Deep Learning Library for Fast Prototyping and Productization
• LEt-SNE: A Hybrid Approach To Data Embedding and Visualization of Hyperspectral Imagery
• Capacity Preserving Mapping for High-dimensional Data Visualization
• Unsupervised Construction of Knowledge Graphs From Text and Code
• Improving the Evaluation of Generative Models with Fuzzy Logic
• Unsupervised Learning of Audio Perception for Robotics Applications: Learning to Project Data to T-SNE/UMAP space
• K-Nearest Neighbor Approximation Via the Friend-of-a-Friend Principle
• Spectral Overlap and a Comparison of Parameter-Free, Dimensionality Reduction Quality Metrics
• Spectral Simplicial Theory for Feature Selection and Applications to Genomics
• Characterizing Certain DNS DDoS Attacks
• Credit Scoring for Micro-Loans
• Enhanced Single-Cell RNA-seq Embedding through Gene Expression and Data-Driven Gene-Gene Interaction Integration
• Understanding Childhood Vulnerability in The City of Surrey
• The decomposition of the higher-order homology embedding constructed from the $k$-Laplacian
• Telephonetic: Making Neural Language Models Robust to ASR and Semantic Noise
• Compressed representation of brain genetic transcription
• Anomaly Detection with Joint Representation Learning of Content and Connection
• Pandemic Policymaking: Learning the Lower Dimensional Manifold of Congressional Responsiveness
• A Fully Tensorized Recurrent Neural Network
• Using Slisemap to interpret physical data
• GENNI: Visualising the Geometry of Equivalences for Neural Network Identifiability
• Vec2GC -- A Graph Based Clustering Method for Text Representations
• Universal and Transferable Attacks on Pathology Foundation Models
• Cartolabe: A Web-Based Scalable Visualization of Large Document Collections
• Interpretable Topic Extraction and Word Embedding Learning using row-stochastic DEDICOM
• Diagnostic Method for Hydropower Plant Condition-based Maintenance combining Autoencoder with Clustering Algorithms
• Geodesic Learning via Unsupervised Decision Forests
• Learning Interpretable Microscopic Features of Tumor by Multi-task Adversarial CNNs To Improve Generalization
• A Visual Analytics Framework for Reviewing Multivariate Time-Series Data with Dimensionality Reduction
• Hyperpolyglot LLMs: Cross-Lingual Interpretability in Token Embeddings
• Deciphering galaxy images using machine vision -- Combining variational autoencoder and principal component analysis for feature extraction
• Who Will Support My Project? Interactive Search of Potential Crowdfunding Investors Through InSearch
• A Review of the State-of-the-Art on Tours for Dynamic Visualization of High-dimensional Data
• An Exploratory Study of COVID-19 Information on Twitter in the Greater Region
• q-SNE: Visualizing Data using q-Gaussian Distributed Stochastic Neighbor Embedding
• Unsupervised Videographic Analysis of Rodent Behaviour
• DRIFT: A Toolkit for Diachronic Analysis of Scientific Literature
• Matrix factorisation and the interpretation of geodesic distance
• Towards Full-Fledged Argument Search: A Framework for Extracting and Clustering Arguments from Unstructured Text
• How Do You Act? An Empirical Study to Understand Behavior of Deep Reinforcement Learning Agents
• Attribute-based Explanations of Non-Linear Embeddings of High-Dimensional Data
• HyperNP: Interactive Visual Exploration of Multidimensional Projection Hyperparameters
• Classifying Complex Dynamical and Stochastic Systems via Physics-Based Recurrence Features
• Harnessing value from data science in business: ensuring explainability and fairness of solutions
• Clusterplot: High-dimensional Cluster Visualization
• Deep learning tackles single-cell analysis A survey of deep learning for scRNA-seq analysis
• Contrastive Learning and Self-Training for Unsupervised Domain Adaptation in Semantic Segmentation
• Natural Adversarial Objects
• ContraCluster: Learning to Classify without Labels by Contrastive Self-Supervision and Prototype-Based Semi-Supervision
• Pretraining Neural Architecture Search Controllers with Locality-based Self-Supervised Learning
• The Hierarchical Structure of Galactic Haloes: Generalised N-Dimensional Clustering with CluSTAR-ND
• Visualization Techniques to Enhance Automated Event Extraction
• Curriculum Offline Imitation Learning
• Bert4XMR: Cross-Market Recommendation with Bidirectional Encoder Representations from Transformer
• Kinetic samplers for neural quantum states
• Methodology for Mining, Discovering and Analyzing Semantic Human Mobility Behaviors
• Personalizing Pre-trained Models
• Unsupervised End-to-End Training with a Self-Defined Target
• Random projection tree similarity metric for SpectralNet
• Robust recognition and exploratory analysis of crystal structures via Bayesian deep learning
• An Interpretable Algorithm for Uveal Melanoma Subtyping from Whole Slide Cytology Images
• Reducing Geographic Performance Differential for Face Recognition
• Improving Metric Dimensionality Reduction with Distributed Topology
• MitoVis: A Visually-guided Interactive Intelligent System for Neuronal Mitochondria Analysis
• Illegible Semantics: Exploring the Design Space of Metal Logos
• An Information-theoretic Visual Analysis Framework for Convolutional Neural Networks
• Estimating the Robustness of Classification Models by the Structure of the Learned Feature-Space
• Partitioned K-nearest neighbor local depth for scalable comparison-based learning
• What do CNN neurons learn: Visualization & Clustering
• Geodesics in fibered latent spaces: A geometric approach to learning correspondences between conditions
• Unsupervised Learning of Neurosymbolic Encoders
• PaccMann${}^{RL}$ on SARS-CoV-2: Designing antiviral candidates with conditional generative models
• CoLA: Weakly-Supervised Temporal Action Localization with Snippet Contrastive Learning
• Continuous Histogram Loss: Beyond Neural Similarity
• Facilitate the Parametric Dimension Reduction by Gradient Clipping
• Can x2vec Save Lives? Integrating Graph and Language Embeddings for Automatic Mental Health Classification
• A Common Operating Picture Framework Leveraging Data Fusion and Deep Learning
• Fixed $\beta$-VAE Encoding for Curious Exploration in Complex 3D Environments
• Differential Similarity in Higher Dimensional Spaces: Theory and Applications
• Novelty-based Generalization Evaluation for Traffic Light Detection
• Learning Physical Concepts in Cyber-Physical Systems: A Case Study
• Docking-based Virtual Screening with Multi-Task Learning
• Interpreting Equivariant Representations
• SCG: Spotting Coordinated Groups in Social Media
• LossPlot: A Better Way to Visualize Loss Landscapes
• Self-supervised similarity search for large scientific datasets
• Active Learning for Argument Mining: A Practical Approach
• AutoDC: Automated data-centric processing
• Interpretable ECG classification via a query-based latent space traversal (qLST)
• Using Deep Learning to Identify Patients with Cognitive Impairment in Electronic Health Records
• Identifying collaborators in large codebases
• Adversarial Scrubbing of Demographic Information for Text Classification
• CO-SNE: Dimensionality Reduction and Visualization for Hyperbolic Data
• GenURL: A General Framework for Unsupervised Representation Learning
• Embed Everything: A Method for Efficiently Co-Embedding Multi-Modal Spaces
• Quantifying the Suicidal Tendency on Social Media: A Survey
• WMDecompose: A Framework for Leveraging the Interpretable Properties of Word Mover's Distance in Sociocultural Analysis
• Does the Layout Really Matter? A Study on Visual Model Accuracy Estimation
• Pairwise Half-graph Discrimination: A Simple Graph-level Self-supervised Strategy for Pre-training Graph Neural Networks
• Improving the Projection of Global Structures in Data through Spanning Trees
• Graph skeletonization of high-dimensional point cloud data via topological method
• ExClus: Explainable Clustering on Low-dimensional Data Representations
• The Curse Revisited: When are Distances Informative for the Ground Truth in Noisy High-Dimensional Data?
• Two Way Adversarial Unsupervised Word Translation
• BUDA.ART: A Multimodal Content-Based Analysis and Retrieval System for Buddha Statues
• Finding Significant Features for Few-Shot Learning using Dimensionality Reduction
• Estimating the electrical power output of industrial devices with end-to-end time-series classification in the presence of label noise
• Graphing else matters: exploiting aspect opinions and ratings in explainable graph-based recommendations
• Multimodal and self-supervised representation learning for automatic gesture recognition in surgical robotics
• Algebraic Machine Learning with an Application to Chemistry
• Latin writing styles analysis with Machine Learning: New approach to old questions
• RRScell method for automated single-cell profiling of multiplexed immunofluorescence cancer tissue
• Leveraging an Efficient and Semantic Location Embedding to Seek New Ports of Bike Share Services
• Sparsity-Probe: Analysis tool for Deep Learning Models
• Similarity networks of ordinal-pattern transitions classify falling paper trajectories
• Label-free Monitoring of Self-Supervised Learning Progress
• Natural language processing for clusterization of genes according to their functions
• Sign and Search: Sign Search Functionality for Sign Language Lexica
• A probabilistic deep learning model to distinguish cusps and cores in dwarf galaxies
• Clustering Malware at Scale: A First Full-Benchmark Study
• ScRAE: Deterministic Regularized Autoencoders with Flexible Priors for Clustering Single-cell Gene Expression Data
• Characterizing Partisan Political Narrative Frameworks about COVID-19 on Twitter
• UMAP-assisted $K$-means clustering of large-scale SARS-CoV-2 mutation datasets
• Measuring inter-cluster similarities with Alpha Shape TRIangulation in loCal Subspaces (ASTRICS) facilitates visualization and clustering of high-dimensional data
• Learning Invariant Representation of Tasks for Robust Surgical State Estimation
• Factoring out prior knowledge from low-dimensional embeddings
• Introduction of a novel word embedding approach based on technology labels extracted from patent data
• Multi-point dimensionality reduction to improve projection layout reliability
• On Information (pseudo) Metric
• Branching embedding: A heuristic dimensionality reduction algorithm based on hierarchical clustering
• Residual networks classify inputs based on their neural transient dynamics
• Modeling Multi-Destination Trips with Sketch-Based Model
• Discovering key topics from short, real-world medical inquiries via natural language processing and unsupervised learning
• A Local Similarity-Preserving Framework for Nonlinear Dimensionality Reduction with Neural Networks
• Visualizing Data Velocity using DSNE
• Explainable Adversarial Attacks in Deep Neural Networks Using Activation Profiles
• Leveraging Domain Adaptation for Low-Resource Geospatial Machine Learning
• Spaceland Embedding of Sparse Stochastic Graphs
• UCSL : A Machine Learning Expectation-Maximization framework for Unsupervised Clustering driven by Supervised Learning
• Interpretable Locally Adaptive Nearest Neighbors
• Contextualisation of eCommerce Users
• Learning Deep-Latent Hierarchies by Stacking Wasserstein Autoencoders
• Semi-Supervised Classification of Social Media Posts: Identifying Sex-Industry Posts to Enable Better Support for Those Experiencing Sex-Trafficking
• Loss Switching Fusion with Similarity Search for Video Classification
• Prediction of Auto Insurance Risk Based on t-SNE Dimensionality Reduction
• Identifying and Analyzing Sepsis States: A Retrospective Study on Patients with Sepsis in ICUs
• Visualizing the geometry of labeled high-dimensional data with spheres
• Learning to recover orientations from projections in single-particle cryo-EM
• A flat persistence diagram for improved visualization of persistent homology
• Learning a Generative Model of Cancer Metastasis
• Domain Conditional Predictors for Domain Adaptation
• Unsupervised discovery of Interpretable Visual Concepts
• Geometric All-Way Boolean Tensor Decomposition
• Leveraging semantically similar queries for ranking via combining representations
• ReLU Code Space: A Basis for Rating Network Quality Besides Accuracy
• Likelihood-Free Gaussian Process for Regression
• An Investigation of the Weight Space to Monitor the Training Progress of Neural Networks
• Supervised Visualization for Data Exploration
• Separating Boundary Points via Structural Regularization for Very Compact Clusters
• MMCGAN: Generative Adversarial Network with Explicit Manifold Prior
• Learning aligned embeddings for semi-supervised word translation using Maximum Mean Discrepancy
• Controlling for sparsity in sparse factor analysis models: adaptive latent feature sharing for piecewise linear dimensionality reduction
• Exploring Language Similarities with Dimensionality Reduction Technique
• A Hierarchical Neural Framework for Classification and its Explanation in Large Unstructured Legal Documents
• Visualizing the Finer Cluster Structure of Large-Scale and High-Dimensional Data
• Deep Learning generated observations of galaxy clusters from dark-matter-only simulations
• Detecting Patterns of Interaction in Temporal Hypergraphs via Edge Clustering
• Visualizing Representations of Adversarially Perturbed Inputs
• Birds of a Feather: Capturing Avian Shape Models from Images
• Hierarchical Models: Intrinsic Separability in High Dimensions
• A Text-Embedding-based Approach to Measure Patent-to-Patent Technological Similarity -- Workflow, Code, and Applications
• DumbleDR: Predicting User Preferences of Dimensionality Reduction Projection Quality