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

arXiv: https://arxiv.org/abs/2306.11797 · HTML: https://mlsanity.com/paper/2306.11797/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 102 references that are in the map.
- First posted on arXiv 20 Jun 2023.

## Builds on (most cited first, 21 of 21)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images](https://mlsanity.com/paper/1412.1897/) (2014)
- [Cyclical Learning Rates for Training Neural Networks](https://mlsanity.com/paper/1506.01186/) (2015)
- [One pixel attack for fooling deep neural networks](https://mlsanity.com/paper/1710.08864/) (2017)
- [Bayesian parameter estimation using conditional variational autoencoders for gravitational-wave astronomy](https://mlsanity.com/paper/1909.06296/) (2019)
- [Deep Learning for Real-time Gravitational Wave Detection and Parameter Estimation: Results with Advanced LIGO Data](https://mlsanity.com/paper/1711.03121/) (2017)
- [Deep Neural Networks to Enable Real-time Multimessenger Astrophysics](https://mlsanity.com/paper/1701.00008/) (2016)
- [Gravitational-wave parameter estimation with autoregressive neural network flows](https://mlsanity.com/paper/2002.07656/) (2020)
- [Convolutional neural networks: a magic bullet for gravitational-wave detection?](https://mlsanity.com/paper/1904.08693/) (2019)
- [Detection of gravitational-wave signals from binary neutron star mergers using machine learning](https://mlsanity.com/paper/2006.01509/) (2020)
- [Source-Agnostic Gravitational-Wave Detection with Recurrent Autoencoders](https://mlsanity.com/paper/2107.12698/) (2021)
- [GanDef: A GAN based Adversarial Training Defense for Neural Network Classifier](https://mlsanity.com/paper/1903.02585/) (2019)
- [From One to Many: A Deep Learning Coincident Gravitational-Wave Search](https://mlsanity.com/paper/2108.10715/) (2021)
- [MLGWSC-1: The first Machine Learning Gravitational-Wave Search Mock Data Challenge](https://mlsanity.com/paper/2209.11146/) (2022)
- [Improving significance of binary black hole mergers in Advanced LIGO data using deep learning : Confirmation of GW151216](https://mlsanity.com/paper/2010.08584/) (2020)
- [Normalizing Flows for Hierarchical Bayesian Analysis: A Gravitational Wave Population Study](https://mlsanity.com/paper/2211.09008/) (2022)
- [Gravitational-wave selection effects using neural-network classifiers](https://mlsanity.com/paper/2007.06585/) (2020)

## Abstract (arXiv)

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. We show that these gains are achieved at practically zero loss in terms of model performance on real LIGO data before and after GAN training. 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. We also report the search sensitivity obtained from an injection study.