Advanced Graph Neural Networks
Advanced Graph Neural Networks is a research topic within Artificial Intelligence. Science Explorer counts 21k research works in it since 1964. 25.1% of them reached the world's top 10% most cited for their field and year.
This cluster of papers focuses on the development, applications, and techniques related to Graph Neural Networks (GNNs) and their variants. It covers topics such as knowledge graph embedding, representation learning, network embedding, deep learning, graph convolutional networks, heterogeneous networks, relational data modeling, signal processing on graphs, and semi-supervised learning.
- Graph Neural Networks
- Knowledge Graph Embedding
- Representation Learning
- Network Embedding
- Deep Learning
- Graph Convolutional Networks
- Heterogeneous Networks
- Relational Data Modeling
- Signal Processing on Graphs
- Semi-Supervised Learning
- Research works
- 21k fractional, since 1964
- In the world top 10%
- 5.3k per year above
- Top-10% rate
- 25.1% share of its works in the world top 10%
- Growth, 2013–17 → 2018–22
- +242% the tick is no change
Which countries lead Advanced Graph Neural Networks research?
By volume, China and the United States publish the most (5.6k and 1.2k works in 2022–2025).
By volume, 2022–2025
- 1 China 5.6k works
- 2 United States 1.2k works
- 3 India 393 works
- 4 Australia 255 works
- 5 Germany 237 works
- 6 United Kingdom 196 works
- 7 South Korea 185 works
- 8 Italy 183 works
- 9 Hong Kong 181 works
- 10 Japan 168 works
How concentrated that is
The same countries as shares of everything the list above accounts for. A node where two countries do two thirds of the work and one spread evenly across twelve read alike as a ranking and not at all alike here.
Shares of the rows listed above, not of the whole node.
Which institutions lead Advanced Graph Neural Networks research?
By volume in 2022–2025, National University of Defense Technology publishes the most Advanced Graph Neural Networks research, followed by Tsinghua University and Beijing University of Posts and Telecommunications.
By volume, 2022–2025
- 1 National University of Defense Technology China 136 works
- 2 Tsinghua University China 100 works
- 3 Beijing University of Posts and Telecommunications China 98 works
- 4 University of Electronic Science and Technology of China China 95 works
- 5 Beihang University China 78 works
- 6 Shanghai Jiao Tong University China 76 works
- 7 Chinese Academy of Sciences China 75 works
- 8 University of Science and Technology of China China 70 works
- 9 Zhejiang University China 69 works
- 10 University of Chinese Academy of Sciences China 67 works
Who are the leading researchers in Advanced Graph Neural Networks?
The most-cited researchers publishing on Advanced Graph Neural Networks include Yoshua Bengio, Wei Liu and Thomas S. Huang.
- 1 Yoshua Bengio 17k citations
- 2 Wei Liu 9.7k citations
- 3 Thomas S. Huang 7.4k citations
- 4 Philip S. Yu 6.6k citations
- 5 Jason Weston 6.3k citations
- 6 Dacheng Tao 6.1k citations
- 7 Guanrong Chen 5.4k citations
Ranked by citations received across their whole record, among researchers with at least three works on this topic.
Where is Advanced Graph Neural Networks research done?
The largest centres of Advanced Graph Neural Networks research in 2022–2025 are Beijing (China), Shanghai (China), Nanjing (China) and Guangzhou (China). Among places with at least 20 works in it, it is an unusually large share of all research in Xining, Guilin and Beijing.
Largest cities, 2022–2025
Where it is the local speciality
- XiningCN · 22.7 works8.1×
- GuilinCN · 55.9 works6.9×
- Beijing24.6 works6.0×
Location quotient: how much more of its research is in Advanced Graph Neural Networks than the world average.
Where is the best place to study Advanced Graph Neural Networks?
Among universities, judged by research, Hong Kong University of Science and Technology, University of Electronic Science and Technology of China and Beijing University of Posts and Telecommunications score highest, combining excellence, specialisation, size, growth and international reach. Research strength is one signal when choosing where to study; it does not measure teaching.
One dot per university in the table below. The upper left is the interesting corner: small places doing unusually strong work.
| # | University | Score | Top 10% | Specialisation | Works | Growth |
|---|---|---|---|---|---|---|
| 1 | Hong Kong University of Science and Technology Hong Kong | 70.6 | 35.7% | 10.9× | 41 | +104.1% |
| 2 | University of Electronic Science and Technology of China China | 70.1 | 30.5% | 8.7× | 95 | +329.6% |
| 3 | Beijing University of Posts and Telecommunications China | 69.2 | 22.8% | 16.5× | 98 | +345.6% |
| 4 | National University of Defense Technology China | 68.9 | 19.4% | 18.2× | 136 | +341.0% |
| 5 | University of Hong Kong Hong Kong | 68.7 | 51.0% | 4.3× | 35 | +447.5% |
| 6 | Renmin University of China China | 67.5 | 29.5% | 13.6× | 43 | +193.4% |
| 7 | Nanyang Technological University Singapore | 66.6 | 38.4% | 5.6× | 44 | +247.0% |
| 8 | Macquarie University Australia | 66.3 | 45.7% | 6.9× | 24 | +198.7% |
| 9 | Tsinghua University China | 64.7 | 36.4% | 5.3× | 100 | +280.2% |
| 10 | Xidian University China | 64.1 | 30.0% | 8.0× | 57 | +499.0% |
Universities only. Score blends excellence (30%), specialisation (25%), size (20%), growth (15%) and international reach (10%), 2015–2022; growth compares 2010–14 with 2015–19.
Is Advanced Graph Neural Networks research growing?
Output in 2018–2022 was 242% higher than in 2013–2017, peaking in 2025. The fastest-growing topics are Advanced Graph Neural Networks.
The same series as a ribbon — one cell per year, darker for more. The line above answers how much; this answers when.
Which topics inside it are moving
Growth and decline on one axis around a shared zero. Two lists side by side hide the thing that matters: whether the growth dwarfs the decline, or the other way round.