https://github.com/shchur/tpp-anomaly-detection

Implementation of "Detecting Anomalous Event Sequences with Temporal Point Processes" (NeurIPS 2021)
https://github.com/shchur/tpp-anomaly-detection

anomaly-detection out-of-distribution-detection pytorch temporal-point-process temporal-point-processes

Last synced: 23 days ago
JSON representation

Implementation of "Detecting Anomalous Event Sequences with Temporal Point Processes" (NeurIPS 2021)

• Host: GitHub
• URL: https://github.com/shchur/tpp-anomaly-detection
• Owner: shchur
• Created: 2021-10-25T19:39:32.000Z (about 3 years ago)
• Default Branch: main
• Last Pushed: 2021-12-30T15:29:00.000Z (almost 3 years ago)
• Last Synced: 2024-10-04T13:32:35.941Z (about 1 month ago)
• Topics: anomaly-detection, out-of-distribution-detection, pytorch, temporal-point-process, temporal-point-processes
• Language: Jupyter Notebook
• Homepage:
• Size: 38.3 MB
• Stars: 25
• Watchers: 1
• Forks: 6
• Open Issues: 1
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Detecting Anomalous Event Sequences with Temporal Point Processes

Pytorch implementation of the paper ["Detecting Anomalous Event Sequences with Temporal Point Processes"](https://papers.neurips.cc/paper/2021/hash/6faa8040da20ef399b63a72d0e4ab575-Abstract.html), by Oleksandr Shchur, Ali Caner Turkmen, Tim Januschowski, Jan Gasthaus, and Stephan Günnemann, NeurIPS 2021.

## Installation

1. Install the dependencies

    ```

    conda env create -f environment.yml

    ```

2. Activate the conda environment

    ```

    conda activate anomaly_tpp

    ```

3. Install the package (this command must be run in the `tpp-anomaly-detection` folder)

    ```

    pip install -e .

    ```

4. Unzip the data

    ```

    unzip data.zip

    ```

## Reproducing the results from the paper

- `notebooks/spp_experiment.ipynb`: Standard Poisson process vs. other toy TPPs (Section 6.1 in the paper).

- `notebooks/multivariate_experiment.ipynb`: Multivariate TPPs inspired by real-world scenarios (Section 6.2).

- `notebooks/real_world_experiment.ipynb`: Real-world datasets (Section 6.3).

## Citation

Please cite our paper if you use the code or the datasets in your own work

```

@article{

    shchur2021detecting,

    title={Detecting Anomalous Event Sequences with Temporal Point Processes},

    author={Oleksandr Shchur and Ali Caner Turkmen and Tim Januschowski and Jan Gasthaus and and Stephan G\"{u}nemann},

    journal={Advances in Neural Information Processing Systems (NeurIPS)},

    year={2021},

}

```