Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/xiaoxinhe/g-retriever
Repository for G-Retriever
https://github.com/xiaoxinhe/g-retriever
Last synced: 8 days ago
JSON representation
Repository for G-Retriever
- Host: GitHub
- URL: https://github.com/xiaoxinhe/g-retriever
- Owner: XiaoxinHe
- License: mit
- Created: 2023-10-25T02:15:26.000Z (about 1 year ago)
- Default Branch: main
- Last Pushed: 2024-03-19T02:54:31.000Z (8 months ago)
- Last Synced: 2024-03-19T03:41:06.726Z (8 months ago)
- Language: Python
- Homepage: https://arxiv.org/abs/2402.07630
- Size: 49.2 MB
- Stars: 101
- Watchers: 3
- Forks: 11
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# G-Retriever
[](https://arxiv.org/abs/2402.07630)
This repository contains the source code for the paper ["G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering"](https://arxiv.org/abs/2402.07630).
We introduce **G-Retriever**, a flexible question-answering framework targeting real-world textual graphs, applicable to multiple applications including scene graph understanding, common sense reasoning, and knowledge graph reasoning.
**G-Retriever** integrates the strengths of Graph Neural Networks (GNNs), Large Language Models (LLMs), and Retrieval-Augmented Generation (RAG), and can be fine-tuned to enhance graph understanding via soft prompting.
## News
[2024.09] [PyG 2.6](https://github.com/pyg-team/pytorch_geometric/releases/tag/2.6.0) now supports **G-Retriever**! 🎉 \[[Dataset](https://pytorch-geometric.readthedocs.io/en/latest/_modules/torch_geometric/datasets/web_qsp_dataset.html)\]\[[Model](https://pytorch-geometric.readthedocs.io/en/latest/generated/torch_geometric.nn.models.GRetriever.html?highlight=gretriever)\]
## Citation
```
@article{he2024g,
title={G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering},
author={He, Xiaoxin and Tian, Yijun and Sun, Yifei and Chawla, Nitesh V and Laurent, Thomas and LeCun, Yann and Bresson, Xavier and Hooi, Bryan},
journal={arXiv preprint arXiv:2402.07630},
year={2024}
}
```
## Environment setup
```
conda create --name g_retriever python=3.9 -y
conda activate g_retriever
# https://pytorch.org/get-started/locally/
conda install pytorch==2.0.1 torchvision==0.15.2 torchaudio==2.0.2 pytorch-cuda=11.8 -c pytorch -c nvidia
python -c "import torch; print(torch.__version__)"
python -c "import torch; print(torch.version.cuda)"
pip install pyg_lib torch_scatter torch_sparse torch_cluster torch_spline_conv -f https://data.pyg.org/whl/torch-2.0.1+cu118.html
pip install peft
pip install pandas
pip install ogb
pip install transformers
pip install wandb
pip install sentencepiece
pip install torch_geometric
pip install datasets
pip install pcst_fast
pip install gensim
pip install scipy=1.12
```
## Data Preprocessing
```
# expla_graphs
python -m src.dataset.preprocess.expla_graphs
python -m src.dataset.expla_graphs
# scene_graphs, might take
python -m src.dataset.preprocess.scene_graphs
python -m src.dataset.scene_graphs
# webqsp
python -m src.dataset.preprocess.webqsp
python -m src.dataset.webqsp
```
## Training
Replace path to the llm checkpoints in the `src/model/__init__.py`, then run
### 1) Inference-Only LLM
```
python inference.py --dataset scene_graphs --model_name inference_llm --llm_model_name 7b_chat
```
### 2) Frozen LLM + Prompt Tuning
```
# prompt tuning
python train.py --dataset scene_graphs_baseline --model_name pt_llm
# G-Retriever
python train.py --dataset scene_graphs --model_name graph_llm
```
### 3) Tuned LLM
```
# finetune LLM with LoRA
python train.py --dataset scene_graphs_baseline --model_name llm --llm_frozen False
# G-Retriever with LoRA
python train.py --dataset scene_graphs --model_name graph_llm --llm_frozen False
```
## Reproducibility
Use `run.sh` to run the codes and reproduce the published results in the main table.