CADET: Calibrated Anomaly Detection for Mitigating Hardness Bias

Authors: Ailin Deng, Adam Goodge, Lang Yi Ang, Bryan Hooi

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

Reproducibility Variable Result LLM Response
Research Type Experimental In this paper, we empirically show the significance of this hardness bias present in a range of recent deep anomaly detection methods. To mitigate this, we propose an efficient and plug-and-play error calibration method which mitigates this hardness bias in the anomaly scoring without the need to retrain the model. We verify the effectiveness of our method on a range of image, time-series, and tabular datasets and against several baseline methods.
Researcher Affiliation Academia 1National University of Singapore 2A*STAR, Singapore {ailin, adam.goodge}@u.nus.edu, joel ang@ibb.a-star.edu.sg, bhooi@comp.nus.edu.sg
Pseudocode Yes Algorithm 1: CADET: Calibrated Anomaly Detection
Open Source Code Yes 1https://github.com/d-ailin/CADET
Open Datasets Yes Specifically, we train an autoencoder (AE) model on the Tshirt class from Fashion-MNIST [Xiao et al., 2017]. The anomalies are from the other nine classes. [...] The experiments are conducted for AE, VAE and other variant models on publicly available image, time series and tabular datasets.
Dataset Splits No The train-test split settings are the same for the baselines and our methods. Full details about datasets, baseline settings, model architectures, hyperparameters, ablation study, etc. can be found in our Supplementary Material.
Hardware Specification No The paper states running times ("the longest running time across all datasets and methods was 1.31s") but does not provide any specific hardware details such as CPU/GPU models, memory, or cloud instance types.
Software Dependencies No The paper does not specify any software dependencies with version numbers (e.g., Python 3.x, PyTorch x.x, TensorFlow x.x, CUDA x.x).
Experiment Setup No Full details about datasets, baseline settings, model architectures, hyperparameters, ablation study, etc. can be found in our Supplementary Material.