Learning by Active Nonlinear Diffusion

05/30/2019
by   Mauro Maggioni, et al.
0

This article proposes an active learning method for high dimensional data, based on intrinsic data geometries learned through diffusion processes on graphs. Diffusion distances are used to parametrize low-dimensional structures on the dataset, which allow for high-accuracy labelings of the dataset with only a small number of carefully chosen labels. The geometric structure of the data suggests regions that have homogeneous labels, as well as regions with high label complexity that should be queried for labels. The proposed method enjoys theoretical performance guarantees on a general geometric data model, in which clusters corresponding to semantically meaningful classes are permitted to have nonlinear geometries, high ambient dimensionality, and suffer from significant noise and outlier corruption. The proposed algorithm is implemented in a manner that is quasilinear in the number of unlabeled data points, and exhibits competitive empirical performance on synthetic datasets and real hyperspectral remote sensing images.

READ FULL TEXT

page 7

page 13

page 16

page 17

research
11/06/2019

Spatially regularized active diffusion learning for high-dimensional images

An active learning algorithm for the classification of high-dimensional ...
research
01/08/2021

Deep Diffusion Processes for Active Learning of Hyperspectral Images

A method for active learning of hyperspectral images (HSI) is proposed, ...
research
04/13/2022

Active Diffusion and VCA-Assisted Image Segmentation of Hyperspectral Images

Hyperspectral images encode rich structure that can be exploited for mat...
research
07/21/2021

Manifold learning-based polynomial chaos expansions for high-dimensional surrogate models

In this work we introduce a manifold learning-based method for uncertain...
research
03/28/2022

Time-inhomogeneous diffusion geometry and topology

Diffusion condensation is a dynamic process that yields a sequence of mu...
research
04/10/2020

Hyperspectral Image Clustering with Spatially-Regularized Ultrametrics

We propose a method for the unsupervised clustering of hyperspectral ima...
research
02/14/2023

Score Approximation, Estimation and Distribution Recovery of Diffusion Models on Low-Dimensional Data

Diffusion models achieve state-of-the-art performance in various generat...

Please sign up or login with your details

Forgot password? Click here to reset