Discriminative Dimensionality Reduction using Deep Neural Networks for Clustering of LIGO Data

TL;DR

This paper introduces neural network-based models for nonlinear, discriminative dimensionality reduction to improve clustering of LIGO gravitational wave data, aiding in glitch classification and discovery of new glitch types.

Contribution

It proposes novel neural network models for discriminative dimensionality reduction that transfer knowledge across domains and facilitate clustering of unlabeled LIGO data.

Findings

Models effectively reduce data dimensionality while preserving class distinctions.

The approach enables discovery of new glitch classes in LIGO data.

Improves clustering accuracy over traditional methods.

Abstract

In this paper, leveraging the capabilities of neural networks for modeling the non-linearities that exist in the data, we propose several models that can project data into a low dimensional, discriminative, and smooth manifold. The proposed models can transfer knowledge from the domain of known classes to a new domain where the classes are unknown. A clustering algorithm is further applied in the new domain to find potentially new classes from the pool of unlabeled data. The research problem and data for this paper originated from the Gravity Spy project which is a side project of Advanced Laser Interferometer Gravitational-wave Observatory (LIGO). The LIGO project aims at detecting cosmic gravitational waves using huge detectors. However non-cosmic, non-Gaussian disturbances known as "glitches", show up in gravitational-wave data of LIGO. This is undesirable as it creates problems for the gravitational wave detection process. Gravity Spy aids in glitch identification with the purpose of understanding their origin. Since new types of glitches appear over time, one of the objective of Gravity Spy is to create new glitch classes. Towards this task, we offer a methodology in this paper to accomplish this.