# Cohort Organized Learning: Clustering Through Agreement

Source: [Cohort Organized Learning: Clustering Through Agreement](<https://www.sota2.com/research/paper/6a3a1355206542251d7c732c>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-06-24T05:00:13.022Z

Authors: Finn Henry O'Shea, Maria Elena Monzani

Published: 2026-06-19T21:00:06.000Z

## Abstract

In this article we describe Cohort Organized Learning (CoOL), a method for clustering data without explicit distance or similarity computations. Herein, we will describe CoOL, derive the gradients determined by expectation maximization to train the networks, show how to monitor convergence during training and evaluate the clusters after training, and discuss a series of examples and use cases. We also discuss CoOL's limitations and future prospects on related tasks. Because CoOL uses neural networks to estimate the clusters, it can be used to cluster any data that can be made compatible and we illustrate this on vector data and images.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Clustering on MNIST 3](<https://www.sota2.com/research/sota/clustering-on-mnist-3.md>): Clustering; MNIST 3; Accuracy: 95.7.

- [Clustering on MNIST 5 (ARI, NMI, ACC, AGR)](<https://www.sota2.com/research/sota/clustering-on-mnist-5-ari-nmi-acc-agr.md>): Clustering; MNIST 5; Accuracy (ACC): 83.4.

- [Clustering on MNIST 7](<https://www.sota2.com/research/sota/clustering-on-mnist-7.md>): Clustering; MNIST 7; Accuracy: 69.7.

- [Clustering on MNIST 9](<https://www.sota2.com/research/sota/clustering-on-mnist-9.md>): Clustering; MNIST 9; Accuracy: 25.9.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2606.21743>)

[PDF](<https://arxiv.org/pdf/2606.21743.pdf>)
