DISCo-Net : Distributed, Interpretable, and Scalable computing for **Co-**authorship Networks

An exponential growth in scientific literature necessitates the development of highly scalable computational tools that can effectively analyze and distill insights from complex, interconnected research landscapes. We introduce Distributed, Interpretable, and Scalable computing for **Co-**authorship Networks (DISCo-Net), a robust and scalable tool engineered to curate and examine large-scale co-authorship networks by harnessing the power of distributed computing and advanced relational database queries.

Contents

• Features
• Usage
  • Initial setup
• Scalable dependencies
• Contributing
• Author information

Features

• Scalable interpretable model
• Distributed computing
• BERT based interpretable inference

Usage

Initial setup

1. Create a Python 3.8 or newer virtual environment.

   conda create -n disconet python=3.8
   source activate disconet
   

2. Install disconet by running,

   pip install pydisconet
   

DISCo-Net extensively utilizes following for scalability

• dask
• duckDB
• multiprocessing

Contributing

If you find a bug 🐛, please open a bug report. If you have an idea for an improvement or new feature 🚀, please open a feature request.

Author information

In case of any questions, please reach out to us at:

• [Swapnil-Keshari] (swk25@pitt.edu)
• [Zarifeh-Heidari-Rarani]
• [Akash-Kishore]
• [Jishnu-Das] (jishnu@pitt.edu)