This repository is a curated list of academic papers and resources focused on neural network pruning. It serves researchers and practitioners in machine learning and deep learning by providing a structured overview of the field, categorized by pruning type and publication year. The primary benefit is a centralized, organized collection of relevant literature, including links to code implementations where available.

How It Works

The repository acts as a comprehensive bibliography, meticulously cataloging research papers on neural network pruning. It categorizes papers by pruning type (e.g., filter pruning, weight pruning, structured pruning) and organizes them by the year of publication. Each entry typically includes the paper's title, venue, pruning type, and, crucially, a link to its code implementation (often PyTorch or TensorFlow). This structured approach allows users to quickly identify and access relevant research and its associated code.

Quick Start & Requirements

This is a curated list, not a software package. No installation or execution is required. Accessing the resources involves browsing the README file and following the provided links to papers and code repositories.

Highlighted Details

• Comprehensive coverage of neural network pruning research from 2015 to the present.
• Categorization by pruning type (Filter, Weight, Structured, Other) and publication venue.
• Inclusion of direct links to code implementations for many papers, primarily in PyTorch and TensorFlow.
• Features a survey paper on structured pruning, with links to both arXiv and IEEE T-PAMI versions.

Maintenance & Community

The repository is maintained by he-y. Contributions are welcomed via pull requests or issues to add new papers or correct existing entries.

Licensing & Compatibility

The repository itself is likely under a permissive license (e.g., MIT, Apache 2.0) as is common for "awesome" lists, but this is not explicitly stated in the README. The licensing of the linked papers and code repositories varies and must be checked individually.

Limitations & Caveats

The repository is a static list and does not provide any tools or frameworks for performing pruning. The availability and maintenance of linked code repositories are external to this project and may vary. Some code links may be broken or point to unmaintained projects.