PyKale: Knowledge-Aware Machine Learning from Multiple Sources in Python

TL;DR

PyKale is a Python library that facilitates knowledge-aware, multimodal, and transfer learning across disciplines, promoting interdisciplinary research with a standardized, resource-efficient API built on PyTorch.

Contribution

It introduces a novel pipeline-based API for knowledge-aware machine learning across multiple data modalities, emphasizing green practices and interdisciplinary applications.

Findings

Supports multimodal learning and transfer learning with deep models

Enables interdisciplinary research in bioinformatics, medical imaging, and more

Reduces redundancy and promotes resource reuse in machine learning workflows

Abstract

Machine learning is a general-purpose technology holding promises for many interdisciplinary research problems. However, significant barriers exist in crossing disciplinary boundaries when most machine learning tools are developed in different areas separately. We present Pykale - a Python library for knowledge-aware machine learning on graphs, images, texts, and videos to enable and accelerate interdisciplinary research. We formulate new green machine learning guidelines based on standard software engineering practices and propose a novel pipeline-based application programming interface (API). PyKale focuses on leveraging knowledge from multiple sources for accurate and interpretable prediction, thus supporting multimodal learning and transfer learning (particularly domain adaptation) with latest deep learning and dimensionality reduction models. We build PyKale on PyTorch and leverage the rich PyTorch ecosystem. Our pipeline-based API design enforces standardization and minimalism, embracing green machine learning concepts via reducing repetitions and redundancy, reusing existing resources, and recycling learning models across areas. We demonstrate its interdisciplinary nature via examples in bioinformatics, knowledge graph, image/video recognition, and medical imaging.