Lu, H. orcid.org/0000-0002-0349-2181, Liu, X., Turner, R. orcid.org/0000-0002-1353-1404 et al. (5 more authors) (Submitted: 2021) PyKale: knowledge-aware machine learning from multiple sources in Python. [Preprint - arXiv]
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.
Metadata
Item Type: | Preprint |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2021 The Author(s). For reuse permissions, please contact the Author(s). |
Keywords: | cs.LG; cs.LG; cs.AI; cs.CV; stat.ML |
Dates: |
|
Institution: | The University of Sheffield |
Academic Units: | The University of Sheffield > Faculty of Engineering (Sheffield) > Department of Computer Science (Sheffield) |
Depositing User: | Symplectic Sheffield |
Date Deposited: | 25 Oct 2022 15:20 |
Last Modified: | 25 Oct 2022 15:20 |
Identification Number: | 10.48550/arXiv.2106.09756 |
Related URLs: | |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:191957 |