naganandy/graph-based-deep-learning-literature

What it solves

This project addresses the challenge of navigating the vast and rapidly growing body of academic research on graph-based deep learning. It provides a centralized, organized repository of literature to help researchers and practitioners find relevant papers without searching through individual conference archives.

How it works

The repository acts as a curated index of research papers, workshops, surveys, and software libraries. It organizes these resources by conference (such as NeurIPS, ICML, ICLR, and CVPR) and by the year of publication. Within each specific conference and year, the papers are further categorized by topic to make finding specific research easier.

Who it’s for

This collection is designed for students, researchers, and machine learning engineers who need a structured way to track developments in graph-based deep learning across various fields like computer vision, data mining, and computational linguistics.

Highlights

• Comprehensive tracking of graph-based deep learning papers from major AI and machine learning conferences.
• Organized by year and conference for easy historical and current research navigation.
• Includes links to essential supplementary resources like surveys, books, and software libraries.
• Categorizes publications by specific topics within each conference folder.