pykale

Knowledge-Aware machine LEarning (KALE): accessible machine learning from multiple sources for interdisciplinary research, part of the 🔥PyTorch ecosystem. ⭐ S

What is pykale?

Knowledge-Aware machine LEarning (KALE): accessible machine learning from multiple sources for interdisciplinary research, part of the 🔥PyTorch ecosystem. ⭐ Star to support our work!

Overview of pykale

What it is

PyKale is a library in the PyTorch ecosystem for knowledge-aware machine learning. It aims to make machine learning more accessible for interdisciplinary research by bridging gaps between data, software, and end users. It focuses on multimodal learning and transfer learning for graphs, images, and videos. PyKale is listed under “Multimodal” in the PyTorch Landscape alongside MMF (Meta), NeMo (NVIDIA), and USB (Microsoft). It enforces standardization and minimalism via green machine learning principles (reduce repetition, reuse existing resources, recycle learning models).

Key features

  • Pipeline-based API with modules: loaddata, prepdata, embed, predict, evaluate, interpret, pipeline.
  • Supports multimodal learning and transfer learning for graphs, images, and videos.
  • Includes supporting models for deep learning and dimensionality reduction.
  • Provides examples with a standardized structure for real applications.
  • Interactive Jupyter notebook tutorials available.
  • Designed for interpretable prediction leveraging knowledge from multiple sources.

Use cases

  • Bioinformatics, graph analysis, image/video recognition, medical imaging.
  • Interdisciplinary research requiring knowledge-aware machine learning from multiple sources.
  • Building reusable workflows for deployable multimodal AI systems.

Getting started

Installation requires Python 3.10, 3.11, or 3.12. It is recommended to install PyTorch matching your hardware first, and if using graphs install PyTorch Geometric. Install PyKale from PyPI:bashpip install pykaleFor detailed installation options, see the repository README. Start with tutorials or examples in the repository.

License and pricing

License: MIT. Open source, no listed pricing.

Based on the project's public README and repository metadata.

Add this badge to your README

Featured on YunoDB Badge styles & help

Maintain this project? Show that it is featured on YunoDB.

Markdown[![Featured on YunoDB](https://yunodb.com/badge/pykalepykale.svg)](https://yunodb.com/tools/pykalepykale?utm_source=github&utm_medium=badge)
HTML<a href="https://yunodb.com/tools/pykalepykale?utm_source=github&utm_medium=badge"><img src="https://yunodb.com/badge/pykalepykale.svg" alt="Featured on YunoDB" height="20"></a>