XAI-Explainability_of_FND_Models
所属分类:图神经网络
开发工具:Jupyter Notebook
文件大小:0KB
下载次数:0
上传日期:2023-11-30 00:10:47
上 传 者:
sh-1993
说明: 该存储库旨在解释最先进的假新闻检测模型。Huggingface模块仅用于解释文本库...
(This repository aims to explain state-of-the-art Fake News Detection models. Huggingface module is intended for explaining only-text-based fake news detection models in Transformers. GNNFakeNews module is an attempt to explain GNNs that are hybrid models for fake news detection using GNNExplainer)
文件列表:
.DS_Store (6148, 2023-12-09)
.idea/ (0, 2023-12-09)
2/ (0, 2023-12-09)
2/.idea/ (0, 2023-12-09)
2/LICENSE (11357, 2023-12-09)
2/data/ (0, 2023-12-09)
2/data/gos_id_time_mapping.pkl (2995950, 2023-12-09)
2/data/gos_id_twitter_mapping.pkl (6197860, 2023-12-09)
2/data/gos_news_list.txt (103523, 2023-12-09)
2/data/pol_id_time_mapping.pkl (327369, 2023-12-09)
2/data/pol_id_twitter_mapping.pkl (676036, 2023-12-09)
2/data/pol_news_list.txt (4868, 2023-12-09)
2/gnn_model/ (0, 2023-12-09)
2/gnn_model/bigcn.py (8178, 2023-12-09)
2/gnn_model/gcnfn.py (5968, 2023-12-09)
2/gnn_model/gnn.py (5821, 2023-12-09)
2/gnn_model/gnncl.py (6101, 2023-12-09)
2/hyper_parameters.md (1420, 2023-12-09)
2/overview.png (303129, 2023-12-09)
2/requirements.txt (73, 2023-12-09)
2/utils/ (0, 2023-12-09)
2/utils/data_loader.py (7447, 2023-12-09)
2/utils/eval_helper.py (1450, 2023-12-09)
2/utils/profile_feature.py (1267, 2023-12-09)
2/utils/twitter_crawler.py (942, 2023-12-09)
(0, 2023-12-09)
.idea/ (0, 2023-12-09)
LICENSE (11357, 2023-12-09)
data/ (0, 2023-12-09)
data/gos_id_time_mapping.pkl (2995950, 2023-12-09)
data/gos_id_twitter_mapping.pkl (6197860, 2023-12-09)
data/gos_news_list.txt (103523, 2023-12-09)
... ...
# XAI: Explainability of FND Models
Author: Manai Mortadha
## Overview
This project focuses on eXplainable Artificial Intelligence (XAI) techniques applied to Financial Neural Decision (FND) models. The primary objective is to enhance transparency and interpretability in the decision-making process of FND models, providing insights into how these models arrive at specific conclusions or predictions in financial scenarios.
## Key Features
- Implementation of various XAI techniques.
- Analysis of interpretability methods for FND models.
- Visual representation of feature importance and model explanations.
## Project Structure
The repository is structured as follows:
- `data/`: Contains datasets and data processing scripts.
- `models/`: Includes the FND models and XAI implementation scripts.
- `notebooks/`: Jupyter notebooks illustrating XAI techniques applied to FND models.
- `results/`: Stores generated output, visualizations, and evaluation metrics.
- `utils/`: Utility functions and helper scripts.
## Installation
To run this project locally, follow these steps:
1. Clone this repository:
```bash
git clone https://github.com/manaimortadha/XAI-Explainability_of_FND_Models.git
```
2. Set up the required environment by installing dependencies:
```bash
pip install -r requirements.txt
```
3. Run the notebooks or scripts in the respective folders.
## Usage
The notebooks provided in the `notebooks/` directory showcase the application of XAI techniques on FND models. Execute these notebooks to explore the explanations and interpretations generated.
## Contributions
Contributions to this project are welcome. If you want to contribute, please follow these guidelines:
- Fork the repository.
- Create a new branch (`git checkout -b feature/your-feature`).
- Make your modifications.
- Commit your changes (`git commit -am 'Add new feature'`).
- Push to the branch (`git push origin feature/your-feature`).
- Create a new Pull Request.
## License
This project is licensed under the [MIT License](https://github.com/MortadhaMannai/XAI-Explainability_of_FND_Models/blob/master/LICENSE).
近期下载者:
相关文件:
收藏者: