LGCLCVSIApr 19, 2020

ktrain: A Low-Code Library for Augmented Machine Learning

arXiv:2004.10703v5167 citations
Originality Synthesis-oriented
AI Analysis

This library addresses the need for easier machine learning application for both beginners and experienced practitioners, though it is incremental as a wrapper around existing tools.

The authors tackled the problem of making machine learning more accessible by developing ktrain, a low-code Python library that simplifies building, training, and applying state-of-the-art models across text, vision, graph, and tabular data, enabling users to solve tasks in as few as three or four lines of code.

We present ktrain, a low-code Python library that makes machine learning more accessible and easier to apply. As a wrapper to TensorFlow and many other libraries (e.g., transformers, scikit-learn, stellargraph), it is designed to make sophisticated, state-of-the-art machine learning models simple to build, train, inspect, and apply by both beginners and experienced practitioners. Featuring modules that support text data (e.g., text classification, sequence tagging, open-domain question-answering), vision data (e.g., image classification), graph data (e.g., node classification, link prediction), and tabular data, ktrain presents a simple unified interface enabling one to quickly solve a wide range of tasks in as little as three or four "commands" or lines of code.

Code Implementations4 repos
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes