https://github.com/abductivelearning/abl-tl
https://github.com/abductivelearning/abl-tl
Last synced: about 1 year ago
JSON representation
- Host: GitHub
- URL: https://github.com/abductivelearning/abl-tl
- Owner: AbductiveLearning
- Created: 2023-12-18T07:00:45.000Z (over 2 years ago)
- Default Branch: main
- Last Pushed: 2024-01-31T06:32:37.000Z (over 2 years ago)
- Last Synced: 2025-04-02T02:46:32.276Z (about 1 year ago)
- Language: Python
- Size: 14.6 KB
- Stars: 5
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
🌟 **New!** [ABLkit](https://github.com/AbductiveLearning/ABLkit) released: A toolkit for Abductive Learning with high flexibility, user-friendly interface, and optimized performance. Welcome to try it out!🚀
# Deciphering Raw Data in Neuro-Symbolic Learning with Provable Guarantees
This is the repository for holding the sample code of [Deciphering Raw Data in Neuro-Symbolic Learning with Provable Guarantees](https://arxiv.org/pdf/2308.10487.pdf) in AAAI 2024.
## Getting Started
Our code relies on PyTorch, which will be automatically installed when you follow the instructions below.
```
conda create -n abl-tl python=3.8
conda activate abl-tl
pip install -r requirements.txt
```
## Running Experiments
- ABL-TL on ConjEq.
```
python main.py --train_loss TL --kb ConjEq
```
- TL-Risk on Conjunction.
```
python main.py --train_loss TL --kb Conjunction
```
## Citing this work
```
@inproceedings{tao2024deciphering,
title={Deciphering Raw Data in Neuro-Symbolic Learning with Provable Guarantees},
author={Tao, Lue and Huang, Yu-Xuan and Dai, Wang-Zhou and Jiang, Yuan},
booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
year={2024}
}
```