Introduction to PyKale, a library for knowledge-aware machine learning from multiple sources
A short introduction to PyKale https://github.com/pykale/pykale, a PyTorch library for multimodal/transfer learning with deep learning and dimensionality reduction on graphs, images, texts, and videos. This video was its v0.1.0b. arXiv preprint for v0.1.0rc2 is at https://arxiv.org/abs/2106.09756.
It adopts a unified pipeline-based API design to enforce standardization and minimalism, aiming to facilitate interdisciplinary, knowledge-aware machine learning research for graphs, images, texts, and videos in applications including bioinformatics, graph analysis, image/video recognition, and medical imaging. Welcome any feedback/contribution!