Towards a robust and reliable deep learning approach for detection of compact binary mergers in gravitational wave data

by   Shreejit Jadhav, et al.

The ability of deep learning (DL) approaches to learn generalised signal and noise models, coupled with their fast inference on GPUs, holds great promise for enhancing gravitational-wave (GW) searches in terms of speed, parameter space coverage, and search sensitivity. However, the opaque nature of DL models severely harms their reliability. In this work, we meticulously develop a DL model stage-wise and work towards improving its robustness and reliability. First, we address the problems in maintaining the purity of training data by deriving a new metric that better reflects the visual strength of the "chirp" signal features in the data. Using a reduced, smooth representation obtained through a variational auto-encoder (VAE), we build a classifier to search for compact binary coalescence (CBC) signals. Our tests on real LIGO data show an impressive performance of the model. However, upon probing the robustness of the model through adversarial attacks, its simple failure modes were identified, underlining how such models can still be highly fragile. As a first step towards bringing robustness, we retrain the model in a novel framework involving a generative adversarial network (GAN). Over the course of training, the model learns to eliminate the primary modes of failure identified by the adversaries. Although absolute robustness is practically impossible to achieve, we demonstrate some fundamental improvements earned through such training, like sparseness and reduced degeneracy in the extracted features at different layers inside the model. Through comparative inference on real LIGO data, we show that the prescribed robustness is achieved at practically zero cost in terms of performance. Through a direct search on  8.8 days of LIGO data, we recover two significant CBC events from GWTC-2.1, GW190519_153544 and GW190521_074359, and report the search sensitivity.


page 2

page 3

page 4

page 7

page 8

page 9

page 15

page 16


Improving significance of binary black hole mergers in Advanced LIGO data using deep learning : Confirmation of GW151216

We present a novel Machine Learning (ML) based strategy to search for co...

Adversarial Robustness of MR Image Reconstruction under Realistic Perturbations

Deep Learning (DL) methods have shown promising results for solving ill-...

RobOT: Robustness-Oriented Testing for Deep Learning Systems

Recently, there has been a significant growth of interest in applying so...

Training Efficiency and Robustness in Deep Learning

Deep Learning has revolutionized machine learning and artificial intelli...

Adversarial Robustness of Deep Convolutional Candlestick Learner

Deep learning (DL) has been applied extensively in a wide range of field...

Adversarial Defense of Image Classification Using a Variational Auto-Encoder

Deep neural networks are known to be vulnerable to adversarial attacks. ...

Denoised Internal Models: a Brain-Inspired Autoencoder against Adversarial Attacks

Despite its great success, deep learning severely suffers from robustnes...

Please sign up or login with your details

Forgot password? Click here to reset