Data

Tools

Indexes

Applications

Experiments

Open Source Science

https://github.com/ai4healthuol/causalconceptts

Repository for the paper 'CausalConceptTS: Causal Attributions for Time Series Classification using High Fidelity Diffusion Models'.

https://github.com/ai4healthuol/causalconceptts

Science Score: 23.0%

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
    Links to: arxiv.org
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (8.9%) to scientific vocabulary

Keywords

causality diffusion-models explainability time-series time-series-classification xai
Last synced: 5 months ago · JSON representation

Repository

Repository for the paper 'CausalConceptTS: Causal Attributions for Time Series Classification using High Fidelity Diffusion Models'.

Basic Info
  • Host: GitHub
  • Owner: AI4HealthUOL
  • License: mit
  • Language: Python
  • Default Branch: main
  • Homepage:
  • Size: 4.07 MB
Statistics
  • Stars: 8
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Topics
causality diffusion-models explainability time-series time-series-classification xai
Created almost 2 years ago · Last pushed 7 months ago
Metadata Files
Readme License

README.md

CausalConceptTS: Causal attributions for time series classification using high fidelity diffusion models

This is the official repository for the paper CausalConceptTS: Causal attributions for time series classification using high fidelity diffusion models

arXiv

In this study, within the context of time series classification, we introduce a novel framework to assess the causal effect of concepts, i.e., predefined segments within a time series, on specific classification outcomes. To achieve this, we leverage state-of-the-art diffusion-based generative models to estimate counterfactual outcomes.

Results

We prove our approach efficace through three tasks:

  • Drought prediction

alt text alt text

  • ECG classification

alt text alt text

  • EEG classification

alt text alt text

Experiments

  • Download the data from this link

  • Place the desired test set under the data directory

  • Follow the instructions under demo.ipynb to obtain the causal effects.

We welcome contributions to improve the reproducibility of this project! Feel free to submit pull requests or open issues.

Reference

bibtex @misc{alcaraz2024causalconceptts, title={CausalConceptTS: Causal Attributions for Time Series Classification using High Fidelity Diffusion Models}, author={Juan Miguel Lopez Alcaraz and Nils Strodthoff}, year={2024}, eprint={2405.15871}, archivePrefix={arXiv}, primaryClass={cs.LG} }

Owner

  • Name: AI4HealthUOL
  • Login: AI4HealthUOL
  • Kind: organization
  • Location: Germany

Public repositories of the AI4Health Division at Oldenburg University

GitHub Events

Total
  • Issues event: 2
  • Watch event: 3
  • Issue comment event: 1
  • Push event: 5
  • Fork event: 2
Last Year
  • Issues event: 2
  • Watch event: 3
  • Issue comment event: 1
  • Push event: 5
  • Fork event: 2

Dependencies

classifier/extensions/cauchy/setup.py pypi
imputer/extensions/cauchy/setup.py pypi