DIRECT: Deep Discriminative Embedding for Clustering of LIGO Data
This work addresses the specific challenge of identifying transient noise in gravitational-wave data for the Gravity Spy Project, representing an incremental improvement in domain-specific clustering methods.
The paper tackles the problem of clustering unlabeled noise features in LIGO data by proposing a deep discriminative embedding function that transfers knowledge from labeled images to isolate new noise classes, aiming to improve noise characterization and removal.
In this paper, benefiting from the strong ability of deep neural network in estimating non-linear functions, we propose a discriminative embedding function to be used as a feature extractor for clustering tasks. The trained embedding function transfers knowledge from the domain of a labeled set of morphologically-distinct images, known as classes, to a new domain within which new classes can potentially be isolated and identified. Our target application in this paper is the Gravity Spy Project, which is an effort to characterize transient, non-Gaussian noise present in data from the Advanced Laser Interferometer Gravitational-wave Observatory, or LIGO. Accumulating large, labeled sets of noise features and identifying of new classes of noise lead to a better understanding of their origin, which makes their removal from the data and/or detectors possible.