Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/khoadoan/GraphOTSim
https://github.com/khoadoan/GraphOTSim
Last synced: about 2 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/khoadoan/GraphOTSim
- Owner: khoadoan
- License: mit
- Created: 2021-05-07T21:18:32.000Z (over 3 years ago)
- Default Branch: main
- Last Pushed: 2022-06-03T06:01:58.000Z (over 2 years ago)
- Last Synced: 2024-06-17T19:03:36.870Z (3 months ago)
- Language: Python
- Size: 1.24 MB
- Stars: 15
- Watchers: 2
- Forks: 3
- Open Issues: 4
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Similarity Computation for Graphs
* Doan & Machanda et al. Interpretable Graph Similarity Computation via Differentiable Optimal Alignment of Node Embeddings (GOTSim). SIGIR 2021. [[Paper](https://people.cs.vt.edu/~reddy/papers/SIGIR21.pdf)] [[Slides](https://github.com/khoadoan/GraphOTSim/blob/main/resources/SIGIR21-fp0937-slides.pdf)] [[Video](https://www.youtube.com/watch?v=IWxxsuFPsgs)]
## Setup the environment
This repository requires python 3.7+ and conda environment. Please refer to `requirements.txt` file for the dependenencies.
## Training and Evaluation GOTSim
GOTSim's training and evaluation processes are encapsulated inside the script `train_gotsim.py'. To train and evaluate using the provided 5-fold evaluation, simply run:
```
export PYTHONPATH=external/:python/:$PYTHONPATH
python python train_gotsim.py --basedir exp/final/PTC_ged/GOTSim/ --dataset data/PTC_ged/
```