Summary of A Comprehensive Survey Of Dynamic Graph Neural Networks: Models, Frameworks, Benchmarks, Experiments and Challenges, by Zhengzhao Feng et al.
A Comprehensive Survey of Dynamic Graph Neural Networks: Models, Frameworks, Benchmarks, Experiments and Challenges
by ZhengZhao Feng, Rui Wang, TianXing Wang, Mingli Song, Sai Wu, Shuibing He
First submitted to arxiv on: 1 May 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper presents a comprehensive survey of Dynamic Graph Neural Networks (GNNs), evaluating their performance, strengths, and limitations. The authors compare 81 dynamic GNN models with a novel taxonomy, 12 training frameworks, and commonly used benchmarks. They also provide experimental results for nine representative models and three frameworks on six standard graph datasets. Evaluation metrics include convergence accuracy, training efficiency, and GPU memory usage. The analysis highlights key challenges and provides principles for future research in the field. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps us understand how to use Dynamic Graph Neural Networks (GNNs) better. GNNs are special kinds of AI that can learn from changing relationships between things, like social networks or traffic patterns. Right now, there are many different ways to build these models, but nobody has looked at all of them together before. This paper is a big review of 81 different models and how they work. The authors also tested some popular models on six different types of data to see which ones perform best. They wanted to know what makes each model good or bad, so they could help others build better GNNs in the future. |
Keywords
» Artificial intelligence » Gnn
