Data

Tools

Indexes

Applications

Experiments

Open Source Science

https://github.com/cgcl-codes/causalnet

https://github.com/cgcl-codes/causalnet

Science Score: 13.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ○
    CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ○
    .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (10.2%) to scientific vocabulary
Last synced: 10 months ago · JSON representation

Repository

Basic Info
  • Host: GitHub
  • Owner: CGCL-codes
  • License: mit
  • Language: Python
  • Default Branch: main
  • Size: 11.4 MB
Statistics
  • Stars: 6
  • Watchers: 2
  • Forks: 1
  • Open Issues: 1
  • Releases: 0
Created about 2 years ago · Last pushed about 2 years ago
Metadata Files
Readme License

README.md

CausalNET

This repository provides the source code and appendix for CausalNET (IJCAI'24).

Environments

shell pip install -r requirements.txt

Experiments

Execute the following steps to replicate our results on the two real datasets (i.e., Micro-24 and Micro-25): ```shell cd ./model conda activate pythonenvsname

before running the following commands, please replace the directory path in '...' by your own settings

'...': Main.py: line22 & line24

python -u main.py -g 1 -task testM24 -opt ./configs/configm24.yaml python -u main.py -g 2 -task testM25 -opt ./configs/configm25.yaml ```

txt Note: (1) the DAG (causal graph) files will be saved in the subdirectory named './dags/final_prob/'. (2) the DAG file for 'dataset_name' will be named as 'dataset_name_i.npy'.

Based on the hyper-parameter settings we provided, the estimated training duration for CausalNET is expected to be 2～6 hours (depending on the status of the hardware devices).

Acknowledgement

Thanks to these excellent open source projects: - TrustworthyAI - Topological Hawkes Process (TNNLS'22) - Transformer Hawkes Process (ICML'20) - CUTS: NEURAL CAUSAL DISCOVERY FROM IRREGULAR TIME-SERIES DATA (ICLR'23)

Citation

If you find the repository helpful, please cite the following paper: tex @inproceedings{hua2024causalnet, title={CausalNET: Unveiling Causal Structures on Event Sequences by Topology-Informed Causal Attention}, author={Hua, Zhu and Hong, Huang and Kehan, Yin and Zejun, Fan and Hai, Jin and Bang, Liu}, booktitle={Proceedings of the 33rd International Joint Conference on Artificial Intelligence}, year={2024} }

Contact

Please feel free to contact us if you have questions, or need explanations: huazhu@hust.edu.cn.

Owner

  • Name: CGCL-codes
  • Login: CGCL-codes
  • Kind: organization

CGCL/SCTS/BDTS Lab

GitHub Events

Total
  • Issues event: 1
  • Watch event: 4
  • Issue comment event: 1
  • Fork event: 1
Last Year
  • Issues event: 1
  • Watch event: 4
  • Issue comment event: 1
  • Fork event: 1

Issues and Pull Requests

Last synced: 10 months ago

All Time
  • Total issues: 1
  • Total pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Total issue authors: 1
  • Total pull request authors: 0
  • Average comments per issue: 0.0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 1
  • Pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Issue authors: 1
  • Pull request authors: 0
  • Average comments per issue: 0.0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
View more stats
Top Authors
Issue Authors
  • Aniq55 (1)
Pull Request Authors
Top Labels
Issue Labels
Pull Request Labels

Dependencies

requirements.txt pypi
  • gcastle ==1.0.4rc1
  • matplotlib ==3.5.3
  • numpy ==1.21.6
  • omegaconf ==2.3.0
  • pandas ==1.3.5
  • scikit_learn ==1.0.2
  • torch ==1.13.1
  • tqdm ==4.66.1