INK is a binary data structure for representing a knowledge graph (KG), taking into account nodes and their neighbourhoods till a certain, specified depth.

This repository contains:

• The code to transform a KG into the binary INK matrix representation
• The code INK Miner code: Semantic rule mining on the INK representation for both task-specific and task-agnostic use cases.

Installation

• pip install https://github.com/IBCNServices/INK
• or clone this repository

Usage

See the example notebook for more information on how to use INK and the INK miner.
The latest documentation is made available by Read the Docs

Publications

Coming soon.

Contributing

Pull requests are welcome.
For major changes, please open an issue first to discuss what you would like to change.

License

IMEC