https://github.com/crisostomi/metric-few-shot-graph

Few-Shot Graph Classification via distance metric learning.
https://github.com/crisostomi/metric-few-shot-graph

distance-metric-learning few-shot-classifcation few-shot-learning graph-classification graph-neural-networks graph-representation-learning

Last synced: 12 days ago
JSON representation

Few-Shot Graph Classification via distance metric learning.

• Host: GitHub
• URL: https://github.com/crisostomi/metric-few-shot-graph
• Owner: crisostomi
• License: mit
• Created: 2022-01-24T10:53:24.000Z (almost 3 years ago)
• Default Branch: main
• Last Pushed: 2023-03-29T18:29:19.000Z (over 1 year ago)
• Last Synced: 2023-06-30T19:33:36.308Z (over 1 year ago)
• Topics: distance-metric-learning, few-shot-classifcation, few-shot-learning, graph-classification, graph-neural-networks, graph-representation-learning
• Language: Python
• Homepage:
• Size: 638 KB
• Stars: 17
• Watchers: 3
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Metric Based Few-Shot Graph Classification



    

    

    



Codebase for the paper [Metric Based Few-Shot Graph Classification](https://proceedings.mlr.press/v198/crisostomi22a.html), published at Learning on Graphs (2022).

## Installation

Setup the development environment:

```bash

conda create --name fs-grl python=3.9

conda activate fs-grl

```

Install PyTorch with CUDA support according to https://pytorch.org/get-started/locally/.

Install PyG

```bash

conda install pyg -c pyg

```

Install the project in edit mode:

```bash

pip install -e .

```

### Download data

Download the versioned datasets:

```bash

dvc pull

dvc checkout

```

### Training a model

You can train and evaluate various families of models by running the corresponding script in the `scripts` folder. For example, to train a Distance Metric Learning model, you can run:

```bash

python fs_grl/scripts/run_dml.py

```