OptIForest: Optimal Isolation Forest for Anomaly Detection

Authors: Haolong Xiang, Xuyun Zhang, Hongsheng Hu, Lianyong Qi, Wanchun Dou, Mark Dras, Amin Beheshti, Xiaolong Xu

IJCAI 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments on a series of benchmarking datasets for comparative and ablation studies demonstrate that our approach can efficiently and robustly achieve better detection performance in general than the state-of-the-arts including the deep learning based methods.
Researcher Affiliation Academia 1Macquarie University 2CSIRO s Data61 3Qufu Normal University 4Nanjing University 5Nanjing University of Information Science and Technology
Pseudocode Yes Algorithm 1 Constructing an Optimal Isolation Tree
Open Source Code Yes The source code is available at https://github.com/xiagll/Opt IForest.
Open Datasets Yes We evaluate all methods on 20 widely-used benchmark datasets [Pang et al., 2019; Han et al., 2022; Li et al., 2022].
Dataset Splits No The paper mentions using 'sampling size' in ablation studies but does not provide specific details on train/validation/test splits, percentages, or cross-validation setup for reproducibility.
Hardware Specification No The paper does not provide any specific details about the hardware used for running the experiments (e.g., GPU/CPU models, memory, or cloud instances).
Software Dependencies No The paper does not provide specific version numbers for any software dependencies used in the experiments (e.g., Python version, library versions).
Experiment Setup No The paper mentions 'optimal parameter settings of the baseline methods' and discusses 'cut threshold' and 'sampling size' in ablation studies, but it does not provide comprehensive details on hyperparameters or other system-level training settings for its own method.