Graph-based Deep Learning Literature is a curated collection of links to conference publications in graph-based deep learning.
The repository addresses the challenge of discovering relevant research in graph neural networks and related areas by organizing publications from major machine learning conferences into a searchable, topic-specific structure. Rather than implementing algorithms or tools, it serves as a structured index that groups papers by conference, year, and research topic, making it easier for researchers and practitioners to find publications across the field's key venues.
Researchers and practitioners working with graph neural networks, graph convolutional networks, or graph representation learning will find this useful as a reference resource for understanding the landscape of published work. The collection spans multiple years and major conferences including NeurIPS, along with supplementary resources such as related workshops, surveys, literature reviews, and software libraries. This approach works best for someone seeking to explore what has been published on specific graph-based deep learning topics rather than needing implementation code or executable tools.
The project maintains an organized structure with publications categorized by topic within each conference and year, supported by links to workshops, surveys, and software resources that complement the primary publication index.
