Data

Tools

Indexes

Applications

Experiments

Open Source Science

project

https://github.com/alessiawelch/project

Science Score: 44.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (4.6%) to scientific vocabulary
Last synced: 9 months ago · JSON representation ·

Repository

Basic Info
  • Host: GitHub
  • Owner: alessiawelch
  • License: mit
  • Language: Jupyter Notebook
  • Default Branch: main
  • Size: 3.29 MB
Statistics
  • Stars: 0
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created over 1 year ago · Last pushed over 1 year ago
Metadata Files
Readme License Citation

README.md

Results

A summarized PDF of the results is available in results_compiled.pdf (download if not immediately visible). For detailed results, including parameters and individual runs, refer to the results folder. Each file is appropriately labeled and stored in corresponding Jupyter Notebook (.ipynb) files for clarity and reproducibility. Plots used in the paper are found in the plots folder.

Runs

The common.py file contains the initialization of the Max, Sum, and Mean aggregators, as well as the newly implemented MaxSum Aggregator using SAGEConv.

Acknowledgments

This codebase was originally forked from Bottleneck repository. We appreciate their contribution.

Owner

  • Login: alessiawelch
  • Kind: user

Citation (CITATION.cff) 

@inproceedings{
    alon2021on,
    title={On the Bottleneck of Graph Neural Networks and its Practical Implications},
    author={Uri Alon and Eran Yahav},
    booktitle={International Conference on Learning Representations},
    year={2021},
    url={https://openreview.net/forum?id=i80OPhOCVH2}
}

GitHub Events

Total
  • Public event: 1
  • Push event: 92
Last Year
  • Public event: 1
  • Push event: 92

Dependencies

requirements.txt pypi
  • attrdict ==2.0.1
  • sklearn *
  • torch >=1.4.0
  • torch-geometric >=1.4.2
  • torch-scatter >=2.0.4
  • torch-sparse >=0.6.0
  • torchvision >=0.5.0