A curated collection of links to conference publications, surveys, and software in graph-based deep learning.
Graph-based Deep Learning Literature is a curated repository of links to academic publications, surveys, and software in the domain of graph-based deep learning. It aggregates research from top-tier conferences and organizes them by conference, year, and topic to help researchers and developers efficiently navigate the literature. The project addresses the challenge of keeping up with the fast-paced advancements in graph neural networks and related methodologies.
Researchers, graduate students, and practitioners in machine learning, artificial intelligence, and data science who are focused on graph-based deep learning, graph neural networks, or related subfields.
It provides a centralized, structured, and up-to-date index of graph-based deep learning resources, saving time on literature searches and offering a historical overview of the field's evolution. Unlike generic academic search engines, it is specifically tailored to graph-based deep learning and includes curated lists of top-cited papers.
links to conference publications in graph-based deep learning
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
Spans publications from major conferences like NeurIPS, ICML, and CVPR back to 2014, providing a broad timeline of the field's evolution as noted in the README.
Groups papers by conference, year, and topic-specific categories, making navigation efficient for targeted research areas.
Includes a list of the top 10 most cited GNN papers and links to surveys, workshops, and software libraries, offering quick access to foundational and supplementary materials.
Hosted on GitHub, it allows for community contributions, helping keep the repository updated with latest conference publications and resources.
The repository is a static list of links without built-in search functionality or dynamic updates, limiting efficiency for specific queries.
Relies solely on external links to papers and resources, which may become broken over time or require institutional access, adding maintenance challenges.
Beyond citation counts, it doesn't provide assessments of paper quality, relevance, or summaries, leaving evaluation to the user.