Neural Contextual Anomaly Detection for Time Series

Authors: Chris U. Carmona, François-Xavier Aubet, Valentin Flunkert, Jan Gasthaus

IJCAI 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We demonstrate empirically on standard benchmark datasets that our approach obtains a state-of-the-art performance in the supervised, semi-supervised, and unsupervised settings.
Researcher Affiliation Industry Chris U. Carmona , Franc ois-Xavier Aubet , Valentin Flunkert , Jan Gasthaus Amazon Research {chrcarm, aubetf, flunkert, gasthaus}@amazon.com
Pseudocode No No pseudocode or clearly labeled algorithm blocks are present in the paper. The steps for the method are described in prose.
Open Source Code Yes open-source code of NCAD is available 2); 2https://github.com/awslabs/gluon-ts/tree/master/src/gluonts/ nursery/ncad
Open Datasets Yes We benchmark our method to others on five datasets... For the multivariate setting, we use: Soil Moisture Active Passive satellite (SMAP) and Mars Science Laboratory rover (MSL), two datasets published by NASA [Hundman et al., 2018]; and Server Machine Dataset (SMD)... For the univariate setting, we use: YAHOO, a dataset by [Yahoo! Labs, 2015]... And KPI, univariate dataset released in the AIOPS data competition by [Tsinghua Netman Lab, 2018].
Dataset Splits Yes For both, following [Ren et al., 2019], we use the last 50% of the time points of each of the time series as test set and split the rest in 30% training and 20% validation set.
Hardware Specification No No specific hardware details (e.g., GPU/CPU models, memory specifications) used for running the experiments are provided in the paper.
Software Dependencies No No specific software dependencies with version numbers (e.g., library names with versions) are listed in the paper.
Experiment Setup Yes Hyperparameters were chosen using the validation set for YAHOO and KPI, and a standard setting is inferred for the other datasets (see extended article for details1).