This repository is a curated list of resources for Automated Machine Learning (AutoML), covering research papers, tools, projects, benchmarks, and commercial products. It serves as a comprehensive reference for researchers, engineers, and practitioners interested in automating the ML pipeline, from neural architecture search to hyperparameter optimization and beyond.

How It Works

The project acts as a knowledge aggregator, systematically categorizing and listing a vast array of AutoML-related materials. It organizes information by AutoML sub-fields (e.g., Neural Network Architecture Search, Hyperparameter Optimization, Meta-learning) and provides links to relevant academic papers, open-source tools, and commercial platforms. This structured approach allows users to quickly navigate the rapidly evolving AutoML landscape.

Quick Start & Requirements

This is a curated list, not a software package. No installation or execution is required.

Highlighted Details

• Extensive collection of research papers, including surveys and specific works on Neural Architecture Search (NAS), Hyperparameter Optimization, and Meta-learning.
• Comprehensive listing of open-source AutoML tools and frameworks like FLAML, AutoGluon, Auto-Sklearn, and Ludwig.
• Includes benchmarks, commercial products, blog posts, courses, and conference materials related to AutoML.
• Covers emerging areas such as AutoML for recommender systems, graph learning, and prompt search for LLMs.

Maintenance & Community

The repository is maintained by windmaple. It appears to be a community-driven effort, with numerous papers and tools contributed by various researchers and organizations. There are no explicit links to community channels or roadmaps provided in the README.

Licensing & Compatibility

The repository itself is a list of links and does not have a specific software license. The licenses of the linked tools and projects vary.

Limitations & Caveats

As a curated list, the content's recency and completeness depend on ongoing community contributions. Some links may become outdated, and the rapid pace of AutoML research means new developments may not be immediately reflected.