Enhancing Fault Detection in Optical Networks with Conditional Denoising Diffusion Probabilistic Models

Meadhbh Healy, Thomas Martini Jørgensen
Proceedings of the 6th Northern Lights Deep Learning Conference (NLDL), PMLR 265:100-109, 2025.

Abstract

The scarcity of high-quality anomalous data often poses a challenge in establishing effective automated fault detection schemes. This study addresses the issue in the context of fault detection in optical fibers using reflectometry data, where noise can obscure the detection of certain known anomalies. We specifically investigate whether classes containing samples of low quality can be boosted with synthetically generated examples characterized by high signal-to-noise ratio (SNR). Specifically, we employ a conditional Denoising Diffusion Probabilistic Model (cDDPM) to generate synthetic data for such classes. It works by learning the characteristics of high SNRs from anomaly classes that are less frequently affected by significant noise. The boosted dataset is compared with a baseline dataset (without the augmented data) by training an anomaly classifier and measuring the performances on a hold-out dataset populated only with high quality traces for all classes. We observe a significant improved performance (Precision, Recall, and F1 Scores) for the noise affected training classes proving the success of our methods.

Cite this Paper

BibTeX
@InProceedings{pmlr-v265-healy25a, title = {Enhancing Fault Detection in Optical Networks with Conditional Denoising Diffusion Probabilistic Models}, author = {Healy, Meadhbh and J{\o}rgensen, Thomas Martini}, booktitle = {Proceedings of the 6th Northern Lights Deep Learning Conference (NLDL)}, pages = {100--109}, year = {2025}, editor = {Lutchyn, Tetiana and Ramírez Rivera, Adín and Ricaud, Benjamin}, volume = {265}, series = {Proceedings of Machine Learning Research}, month = {07--09 Jan}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v265/main/assets/healy25a/healy25a.pdf}, url = {https://proceedings.mlr.press/v265/healy25a.html}, abstract = {The scarcity of high-quality anomalous data often poses a challenge in establishing effective automated fault detection schemes. This study addresses the issue in the context of fault detection in optical fibers using reflectometry data, where noise can obscure the detection of certain known anomalies. We specifically investigate whether classes containing samples of low quality can be boosted with synthetically generated examples characterized by high signal-to-noise ratio (SNR). Specifically, we employ a conditional Denoising Diffusion Probabilistic Model (cDDPM) to generate synthetic data for such classes. It works by learning the characteristics of high SNRs from anomaly classes that are less frequently affected by significant noise. The boosted dataset is compared with a baseline dataset (without the augmented data) by training an anomaly classifier and measuring the performances on a hold-out dataset populated only with high quality traces for all classes. We observe a significant improved performance (Precision, Recall, and F1 Scores) for the noise affected training classes proving the success of our methods.} }
Endnote
%0 Conference Paper %T Enhancing Fault Detection in Optical Networks with Conditional Denoising Diffusion Probabilistic Models %A Meadhbh Healy %A Thomas Martini Jørgensen %B Proceedings of the 6th Northern Lights Deep Learning Conference (NLDL) %C Proceedings of Machine Learning Research %D 2025 %E Tetiana Lutchyn %E Adín Ramírez Rivera %E Benjamin Ricaud %F pmlr-v265-healy25a %I PMLR %P 100--109 %U https://proceedings.mlr.press/v265/healy25a.html %V 265 %X The scarcity of high-quality anomalous data often poses a challenge in establishing effective automated fault detection schemes. This study addresses the issue in the context of fault detection in optical fibers using reflectometry data, where noise can obscure the detection of certain known anomalies. We specifically investigate whether classes containing samples of low quality can be boosted with synthetically generated examples characterized by high signal-to-noise ratio (SNR). Specifically, we employ a conditional Denoising Diffusion Probabilistic Model (cDDPM) to generate synthetic data for such classes. It works by learning the characteristics of high SNRs from anomaly classes that are less frequently affected by significant noise. The boosted dataset is compared with a baseline dataset (without the augmented data) by training an anomaly classifier and measuring the performances on a hold-out dataset populated only with high quality traces for all classes. We observe a significant improved performance (Precision, Recall, and F1 Scores) for the noise affected training classes proving the success of our methods.
APA
Healy, M. & Jørgensen, T.M.. (2025). Enhancing Fault Detection in Optical Networks with Conditional Denoising Diffusion Probabilistic Models. Proceedings of the 6th Northern Lights Deep Learning Conference (NLDL), in Proceedings of Machine Learning Research 265:100-109 Available from https://proceedings.mlr.press/v265/healy25a.html.

Related Material