Science Explorer Back to mapMap
Discussion
Topic · Artificial Intelligence

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. 9.7% 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%
2k
per year above
Top-10% rate
9.7%
share of its works in the world top 10%
Growth, 2018-21 → 2022-25
+120%
the tick is no change
Largest producer
China
65% of the 10 largest, 2022-now
Advanced Graph Neural Networks

Which countries lead Advanced Graph Neural Networks research?

By volume, China and the United States publish the most (7.4k and 1.5k works in 2022-now).

By volume, 2022-now

  1. 1 China 7.4k works
  2. 2 United States 1.5k works
  3. 3 India 602 works
  4. 4 Germany 317 works
  5. 5 Australia 315 works
  6. 6 United Kingdom 277 works
  7. 7 South Korea 245 works
  8. 8 Italy 231 works
  9. 9 Japan 208 works
  10. 10 France 201 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.

China: 65.3%United States: 13.5%India: 5.3%Germany: 2.8%6 others listed: 13.1%65%largest
China7,382 · 65.3%United States1,533 · 13.5%India602 · 5.3%Germany317 · 2.8%6 others listed1,478 · 13.1%

Shares of the rows listed above, not of the whole node.

Which institutions lead Advanced Graph Neural Networks research?

By volume in 2022-now, Chinese Academy of Sciences publishes the most Advanced Graph Neural Networks research, followed by National University of Defense Technology and Beijing University of Posts and Telecommunications.

By volume, 2022-now

  1. 1 Chinese Academy of SciencesChina 250 works
  2. 2 National University of Defense TechnologyChina 165 works
  3. 3 Beijing University of Posts and TelecommunicationsChina 122 works
  4. 4 Tsinghua UniversityChina 122 works
  5. 5 University of Electronic Science and Technology of ChinaChina 113 works
  6. 6 Shanghai Jiao Tong UniversityChina 98 works
  7. 7 Beihang UniversityChina 96 works
  8. 8 Zhejiang UniversityChina 89 works
  9. 9 Peking UniversityChina 89 works
  10. 10 University of Science and Technology of ChinaChina 87 works

Who are the leading researchers in Advanced Graph Neural Networks?

The most-cited researchers publishing on Advanced Graph Neural Networks include Yoshua Bengio, Kieron Burke and Yann LeCun.

  1. 1 Yoshua Bengio Canada 476k citations
  2. 2 Kieron Burke United States 276k citations
  3. 3 Yann LeCun United States 256k citations
  4. 4 James Thomas United Kingdom 242k citations
  5. 5 Li Fei-Fei United States 225k citations
  6. 6 Kai You Wang China 224k citations
  7. 7 Albert-Ĺaszló Barabási United States 223k citations
  8. 8 Lei Jiang China 214k citations
  9. 9 Harry Eugene Stanley United States 198k citations
  10. 10 Michael I. Jordan United States 182k citations

Ranked by citations received across their whole record, among researchers with at least three works on this topic.

What are the most cited papers in Advanced Graph Neural Networks?

The most cited paper in Advanced Graph Neural Networks is "Detecting Functionality-Specific Vulnerabilities via Retrieving Individual Functionality-Equivalent APIs in Open-Source Repositories" (Chen, Tianyu, Wang, Zeyu, Li, Lin et al., 2025), with 16,321 citations. Next come "A tutorial on spectral clustering" (10,505) and "A Comprehensive Survey on Graph Neural Networks" (10,010).

Most cited papers
#PaperReleasedCitations
1 Detecting Functionality-Specific Vulnerabilities via Retrieving Individual Functionality-Equivalent APIs in Open-Source Repositories Chen, Tianyu, Wang, Zeyu, Li, Lin et al. · Leibniz international proceedings in informatics Conference paperOpen access 2025 16,321
2 A tutorial on spectral clustering Ulrike von Luxburg · Statistics and Computing Open access 21 Aug 2007 10,505
3 A Comprehensive Survey on Graph Neural Networks Zonghan Wu, Shirui Pan, Fengwen Chen et al. · IEEE Transactions on Neural Networks and Learning Systems Open access 24 Mar 2020 10,010
4 The Graph Neural Network Model Franco Scarselli, M. Gori, Ah Chung Tsoi et al. · IEEE Transactions on Neural Networks Open access 10 Dec 2008 9,764
5 Authoritative sources in a hyperlinked environment Jon Kleinberg · Journal of the ACM Open access Sep 1999 9,110
All 98 most cited papers, with filters and sorting

Where is Advanced Graph Neural Networks research done?

The largest centres of Advanced Graph Neural Networks research in 2022-now 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-now

  1. 1 BeijingChina 1.5k works
  2. 2 ShanghaiChina 489 works
  3. 3 NanjingChina 345 works
  4. 4 GuangzhouChina 328 works
  5. 5 WuhanChina 322 works
  6. 6 HangzhouChina 311 works
  7. 7 ChangshaChina 290 works
  8. 8 Xi'anChina 285 works
  9. 9 ChengduChina 251 works
  10. 10 HefeiChina 216 works

Where it is the local speciality

  1. XiningCN · 26.9 works7.0×
  2. GuilinCN · 65.6 works6.2×
  3. Beijing28.5 works5.7×
← less than its size predicts1×more →

Location quotient: how much more of its research is in Advanced Graph Neural Networks than the world average.

See Advanced Graph Neural Networks on the map

Where is the best place to study Advanced Graph Neural Networks?

Among universities, judged by research, University of Hong Kong, National University of Singapore and Tsinghua University 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.

0%20%40%mean 18.81%fractional works in this field (log) →share of work in the world top 10% →University of Hong K…National University …Nanyang Technologica…Tsinghua University
above the meannear itbelow it

One dot per university in the first ten of the table below, at the default weights. The upper left is the interesting corner: small places doing unusually strong work.

Excellenceshare of its work in the world top 10%, 2022-now and all time averaged
40%
Specialisationhow much of its work is in this field, counted up to 10× the world share
10%
Sizeits output in this field, on a log scale
30%
Growthoutput growth, counted from -20% to +20%
10%
Internationalshare of its work with a co-author abroad
10%
Each slider sets a weight; the share it gets of the score is beside it.
#UniversityScoreTop 10%SpecialisationWorksGrowth
1University of Hong KongChina 80.426.1%4.3×45 +299.3%
2National University of SingaporeSingapore 72.019.9%3.8×51 +130.8%
3Tsinghua UniversityChina 71.615.8%4.7×122 +21.6%
4Nanyang Technological UniversitySingapore 70.817.7%6.3×56 +111.5%
5Hong Kong University of Science and TechnologyChina 70.816.8%10.7×49 +120.4%
6Hong Kong Polytechnic UniversityChina 70.816.5%4.8×46 +154.9%
7The University of QueenslandAustralia 67.929.5%1.6×17 +20.3%
8University of Science and Technology of ChinaChina 67.415.4%6.6×87 +121.4%
9University of Electronic Science and Technology of ChinaChina 66.413.1%9.0×113 +161.8%
10Zhejiang UniversityChina 66.117.3%3.0×89 +183.5%

Universities only. The score blends excellence (40%), size (30%), specialisation (10%), growth (10%), international reach (10%), 2022-now; growth compares 2018-21 with 2022-25 and counts up to +20%, since a jump from a small base is mostly noise.

Every institution in Advanced Graph Neural Networks, country by country

Is Advanced Graph Neural Networks research growing?

Output in 2022-2025 was 120% higher than in 2018-2021, peaking in 2025. The fastest-growing topics are Advanced Graph Neural Networks.

still counting19801990200020102020
grewheldshrank

The same series as a ribbon: one cell per year, darker for more. The line above answers how much; this answers when.

Its share of all research

Growing output can still be a shrinking share: all of science grows. This is Advanced Graph Neural Networks as a percentage of every work published that year, 0.040% in 2024.

still counting0.025%0.050%0.075%Advanced Graph Neural Networks0.062% in 202519801990200020102020

Fractional works of Advanced Graph Neural Networks over all fractional works that year. How the balance of science has shifted.

How much of it reaches the world top 10%

Year by year.

still counting5%10%15%Advanced Graph Neural Networks9.6% in 202520102020

Of each year's works in it, the share that reached the world's 10% most cited for their field and year. A field is the world for its own topics, so there is no other line to hold it against.

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.

Questions people ask

Who leads graph neural network research?

By volume in 2022-now, Chinese Academy of Sciences publishes the most Advanced Graph Neural Networks research, followed by National University of Defense Technology and Beijing University of Posts and Telecommunications. By volume, China and the United States publish the most (7.4k and 1.5k works in 2022-now).

All 1,273 questions in the Question Catalogue

Discussion

Ask a question or share a note about Advanced Graph Neural Networks. Posts are plain text and can be reported.