Transfer Anomaly Detection by Inferring Latent Domain Representations

Authors: Atsutoshi Kumagai, Tomoharu Iwata, Yasuhiro Fujiwara

NeurIPS 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental The effectiveness of the proposed method is demonstrated through experiments using one synthetic and four real-world datasets.
Researcher Affiliation Industry Atsutoshi Kumagai NTT Software Innovation Center NTT Secure Platform Laboratories atsutoshi.kumagai.ht@hco.ntt.co.jp Tomoharu Iwata NTT Communication Science Laboratories tomoharu.iwata.gy@hco.ntt.co.jp Yasuhiro Fujiwara NTT Communication Science Laboratories yasuhiro.fujiwara.kh@hco.ntt.co.jp
Pseudocode No The paper describes the proposed method and equations but does not include a formal pseudocode or algorithm block.
Open Source Code No The proposed method was implemented by Chainer [45].
Open Datasets Yes We used four real-world public datasets: MNIST-r, Anuran Calls, Landmine, and Io T. ... Due to the length limit of the paper, the details of the datasets including download links are provided in the supplemental material.
Dataset Splits No We selected hyperparameters using average validation AUC on the source domains for all methods except for AE.
Hardware Specification Yes We used the following setup: CPU was Intel Xeon E5-2660v3 2.6 GHz, the memory size was 128 GB, and GPU was NVIDIA Tesla k80.
Software Dependencies No The proposed method was implemented by Chainer [45].
Experiment Setup Yes We set the hyperparameters as follows: the regularization parameter of the AUC loss λ was 104, the dimension of the latent domain vector K was 20, the regularization parameter of the latent domain vector β was one, and the sample size of the reparametrization trick L was one.