k-Nearest Neighbors

Also known as KNN

k-Nearest Neighbors methods make predictions or retrieve examples by comparing a query with nearby observations, supporting classification, regression, clustering, and graph learning. Approaches include fixed or weighted neighbor sets, adaptive neighborhood sizes and radii, learned or geometry-aware distances, neighborhood graphs, conformal uncertainty estimates, and exact or approximate search indexes. Research studies consistency and convergence under settings such as dependent data, and evaluates methods on image, graph, time-series, and high-dimensional embedding tasks. A central challenge is that neighborhood quality depends on the representation and distance, especially in high dimensions, while speed, robustness, and reliable uncertainty can call for different design choices.

Latest papers

34 papers9 papers in the last four weeks, up 125% on the four weeks before. 0.1% of all new papers.

DANCE: Doubly Adaptive Neighborhood Conformal Estimation
Feb 24, 2026Brandon R. Feng, Brian J. Reich, Daniel Beaglehole +7Conformal Prediction Classification
Department of Statistics, North Carolina State University, Raleigh, NC, USA · Amazon.com, Seattle, WA, USA · Department of Computer Science, University of California San Diego, San Diego, CA, USA +2
GICDM: Mitigating Hubness for Reliable Distance-Based Generative Model Evaluation
Feb 18, 2026Nicolas Salvy, Hugues Talbot, Bertrand ThirionGenerative AI Evaluation k-Nearest Neighbors
Inria, Palaiseau, France · CentraleSupélec, Gif-sur-Yvette, France · Université Paris-Saclay, Gif-sur-Yvette, France +1
Unifying Convolution and Attention via Convolutional Nearest Neighbors
Nov 18, 2025Mingi Kang, Jeová Farias Sales Rocha NetoHybrid CNN-Transformer Architectures Self-Attention
Bowdoin College
Conformal and kNN Predictive Uncertainty Quantification Algorithms in Metric Spaces
Jul 21, 2025Gábor Lugosi, Marcos MatabuenaConformal Prediction k-Nearest Neighbors
Department of Economics and Business, Pompeu Fabra University, Barcelona, Spain · ICREA, Pg. Lluís Companys 23, 08010 Barcelona, Spain · Barcelona Graduate School of Economics +3

Feb 24, 2026J/K move · Enter open · S save

DANCE: Doubly Adaptive Neighborhood Conformal Estimation

Brandon R. Feng, Brian J. Reich, Daniel Beaglehole, Xihaier Luo+6

Department of Statistics, North Carolina State University, Raleigh, NC, USA · Amazon.com, Seattle, WA, USA · Department of Computer Science, University of California San Diego, San Diego, CA, USA+2

Conformal Prediction Classification k-Nearest Neighbors

Open paper AskPDF arXiv

The recent developments of complex deep learning models have led to unprecedented ability to accurately predict across multiple data representation types. Conformal prediction for uncertainty quantification of these models has risen in popularity, providing adaptive, statistically-valid prediction sets. For classification tasks, conformal methods have typically focused on utilizing logit scores. For pre-trained models, however, this can result in inefficient, overly conservative set sizes when not calibrated towards the target task. We propose DANCE, a doubly locally adaptive nearest-neighbor based conformal algorithm combining two novel nonconformity scores directly using the data's embedded representation. DANCE first fits a task-adaptive kernel regression model from the embedding layer before using the learned kernel space to produce the final prediction sets for uncertainty quantification. We test against state-of-the-art local, task-adapted and zero-shot conformal baselines, demonstrating DANCE's superior blend of set size efficiency and robustness across various datasets.

Latest papers

DANCE: Doubly Adaptive Neighborhood Conformal Estimation

GICDM: Mitigating Hubness for Reliable Distance-Based Generative Model Evaluation

Unifying Convolution and Attention via Convolutional Nearest Neighbors

Conformal and kNN Predictive Uncertainty Quantification Algorithms in Metric Spaces