DeepAI AI Chat
Log In Sign Up

Unsupervised Co-Learning on G-Manifolds Across Irreducible Representations

by   Yifeng Fan, et al.
University of Illinois at Urbana-Champaign
The University of Chicago

We introduce a novel co-learning paradigm for manifolds naturally equipped with a group action, motivated by recent developments on learning a manifold from attached fibre bundle structures. We utilize a representation theoretic mechanism that canonically associates multiple independent vector bundles over a common base manifold, which provides multiple views for the geometry of the underlying manifold. The consistency across these fibre bundles provide a common base for performing unsupervised manifold co-learning through the redundancy created artificially across irreducible representations of the transformation group. We demonstrate the efficacy of the proposed algorithmic paradigm through drastically improved robust nearest neighbor search and community detection on rotation-invariant cryo-electron microscopy image analysis.


Disentangling by Subspace Diffusion

We present a novel nonparametric algorithm for symmetry-based disentangl...

Discretization of Parametrizable Signal Manifolds

Transformation-invariant analysis of signals often requires the computat...

Learning Smooth Pattern Transformation Manifolds

Manifold models provide low-dimensional representations that are useful ...

Manifold learning with approximate nearest neighbors

Manifold learning algorithms are valuable tools for the analysis of high...

Manifold Learning Benefits GANs

In this paper, we improve Generative Adversarial Networks by incorporati...

Representation Theoretic Patterns in Multi-Frequency Class Averaging for Three-Dimensional Cryo-Electron Microscopy

We develop in this paper a novel intrinsic classification algorithm -- m...