Semi-Supervised Manifold Learning with Complexity Decoupled Chart Autoencoders

08/22/2022
by   Stefan C. Schonsheck, et al.
0

Autoencoding is a popular method in representation learning. Conventional autoencoders employ symmetric encoding-decoding procedures and a simple Euclidean latent space to detect hidden low-dimensional structures in an unsupervised way. This work introduces a chart autoencoder with an asymmetric encoding-decoding process that can incorporate additional semi-supervised information such as class labels. Besides enhancing the capability for handling data with complicated topological and geometric structures, these models can successfully differentiate nearby but disjoint manifolds and intersecting manifolds with only a small amount of supervision. Moreover, this model only requires a low complexity encoder, such as local linear projection. We discuss the theoretical approximation power of such networks that essentially depends on the intrinsic dimension of the data manifold and not the dimension of the observations. Our numerical experiments on synthetic and real-world data verify that the proposed model can effectively manage data with multi-class nearby but disjoint manifolds of different classes, overlapping manifolds, and manifolds with non-trivial topology.

READ FULL TEXT
research
08/21/2019

A Neural Network for Semi-Supervised Learning on Manifolds

Semi-supervised learning algorithms typically construct a weighted graph...
research
03/17/2023

Deep Nonparametric Estimation of Intrinsic Data Structures by Chart Autoencoders: Generalization Error and Robustness

Autoencoders have demonstrated remarkable success in learning low-dimens...
research
10/24/2022

Atlas flow : compatible local structures on the manifold

In this paper, we focus on the intersections of a manifold's local struc...
research
12/20/2019

Chart Auto-Encoders for Manifold Structured Data

Auto-encoding and generative models have made tremendous successes in im...
research
12/21/2017

Deep Unsupervised Clustering Using Mixture of Autoencoders

Unsupervised clustering is one of the most fundamental challenges in mac...
research
06/07/2021

Multi-chart flows

We present Multi-chart flows, a flow-based model for concurrently learni...
research
12/11/2018

Adversarial Autoencoders with Constant-Curvature Latent Manifolds

Constant-curvature Riemannian manifolds (CCMs) have been shown to be ide...

Please sign up or login with your details

Forgot password? Click here to reset