Deep Contextual Novelty Detection with Context Prediction

Ellen Rushe, Brian Mac Namee
Proceedings of the Fourth International Workshop on Learning with Imbalanced Domains: Theory and Applications, PMLR 183:127-138, 2022.

Abstract

Contextual novelty detection models detect novelties with respect to a given context. This is crucial in streaming scenarios where the definition of both normal and novel evolve over time. Such models however require contextual labels not only for training but also for detection during deployment. This creates an often unreasonable burden for additional contextual labels during the deployment of these models. In order to eliminate the need for these labels, we propose to predict this contextual information using an auxiliary prediction strategy which takes advantage of the rarity of novel examples, allowing these labels to instead be inferred. The inferred labels are then used as a conditioning criterion for deep autoencoders. We evaluate our approach on a large, public industrial machine sound dataset and show that our approach can successfully recognise context and use this to effectively condition novelty detection models, allowing them to outperform their unconditioned counterparts.

Cite this Paper

BibTeX
@InProceedings{pmlr-v183-rushe22a, title = {Deep Contextual Novelty Detection with Context Prediction}, author = {Rushe, Ellen and Namee, Brian Mac}, booktitle = {Proceedings of the Fourth International Workshop on Learning with Imbalanced Domains: Theory and Applications}, pages = {127--138}, year = {2022}, editor = {Moniz, Nuno and Branco, Paula and Torgo, Luís and Japkowicz, Nathalie and Wozniak, Michal and Wang, Shuo}, volume = {183}, series = {Proceedings of Machine Learning Research}, month = {23 Sep}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v183/rushe22a/rushe22a.pdf}, url = {https://proceedings.mlr.press/v183/rushe22a.html}, abstract = {Contextual novelty detection models detect novelties with respect to a given context. This is crucial in streaming scenarios where the definition of both normal and novel evolve over time. Such models however require contextual labels not only for training but also for detection during deployment. This creates an often unreasonable burden for additional contextual labels during the deployment of these models. In order to eliminate the need for these labels, we propose to predict this contextual information using an auxiliary prediction strategy which takes advantage of the rarity of novel examples, allowing these labels to instead be inferred. The inferred labels are then used as a conditioning criterion for deep autoencoders. We evaluate our approach on a large, public industrial machine sound dataset and show that our approach can successfully recognise context and use this to effectively condition novelty detection models, allowing them to outperform their unconditioned counterparts.} }
Endnote
%0 Conference Paper %T Deep Contextual Novelty Detection with Context Prediction %A Ellen Rushe %A Brian Mac Namee %B Proceedings of the Fourth International Workshop on Learning with Imbalanced Domains: Theory and Applications %C Proceedings of Machine Learning Research %D 2022 %E Nuno Moniz %E Paula Branco %E Luís Torgo %E Nathalie Japkowicz %E Michal Wozniak %E Shuo Wang %F pmlr-v183-rushe22a %I PMLR %P 127--138 %U https://proceedings.mlr.press/v183/rushe22a.html %V 183 %X Contextual novelty detection models detect novelties with respect to a given context. This is crucial in streaming scenarios where the definition of both normal and novel evolve over time. Such models however require contextual labels not only for training but also for detection during deployment. This creates an often unreasonable burden for additional contextual labels during the deployment of these models. In order to eliminate the need for these labels, we propose to predict this contextual information using an auxiliary prediction strategy which takes advantage of the rarity of novel examples, allowing these labels to instead be inferred. The inferred labels are then used as a conditioning criterion for deep autoencoders. We evaluate our approach on a large, public industrial machine sound dataset and show that our approach can successfully recognise context and use this to effectively condition novelty detection models, allowing them to outperform their unconditioned counterparts.
APA
Rushe, E. & Namee, B.M.. (2022). Deep Contextual Novelty Detection with Context Prediction. Proceedings of the Fourth International Workshop on Learning with Imbalanced Domains: Theory and Applications, in Proceedings of Machine Learning Research 183:127-138 Available from https://proceedings.mlr.press/v183/rushe22a.html.

Related Material