Science Explorer Back to mapMap
Discussion
Topic · Artificial Intelligence

Explainable Artificial Intelligence (XAI)

Explainable Artificial Intelligence (XAI) is a research topic within Artificial Intelligence. Science Explorer counts 16k research works in it since 1965. 10.1% of them reached the world's top 10% most cited for their field and year.

This cluster of papers focuses on Explainable Artificial Intelligence (XAI) and the development of interpretable models, visual explanations, and responsible machine learning interpretability. It explores concepts, challenges, and opportunities in XAI, including the use of gradient-based localization, understanding deep neural networks, feature importance, and addressing black box models. The papers also discuss the responsibility and ethical considerations in AI.

  • Interpretable Models
  • Machine Learning Interpretability
  • Visual Explanations
  • XAI Concepts
  • Model Interpretability
  • Gradient-Based Localization
  • Deep Neural Networks
  • Feature Importance
  • Black Box Models
  • Responsibility in AI
Research works
16k
fractional, since 1965
In the world top 10%
1.7k
per year above
Top-10% rate
10.1%
share of its works in the world top 10%
Growth, 2018-21 → 2022-25
+321%
the tick is no change
Largest producer
United States
33% of the 10 largest, 2022-now
Explainable Artificial Intelligence (XAI)

Which countries lead Explainable Artificial Intelligence (XAI) research?

By volume, the United States and China publish the most (3k and 1.6k works in 2022-now).

By volume, 2022-now

  1. 1 United States 3k works
  2. 2 China 1.6k works
  3. 3 India 1.4k works
  4. 4 Germany 762 works
  5. 5 United Kingdom 696 works
  6. 6 Italy 457 works
  7. 7 Canada 368 works
  8. 8 Australia 300 works
  9. 9 France 298 works
  10. 10 Japan 254 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.

United States: 32.8%China: 17.2%India: 15.7%Germany: 8.3%6 others listed: 25.9%33%largest
United States3,002 · 32.8%China1,578 · 17.2%India1,441 · 15.7%Germany762 · 8.3%6 others listed2,373 · 25.9%

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

Which institutions lead Explainable Artificial Intelligence (XAI) research?

By volume in 2022-now, Centre National de la Recherche Scientifique publishes the most Explainable Artificial Intelligence (XAI) research, followed by Carnegie Mellon University and Chinese Academy of Sciences.

By volume, 2022-now

  1. 1 Centre National de la Recherche ScientifiqueFrance 78 works
  2. 2 Carnegie Mellon UniversityUnited States 55 works
  3. 3 Chinese Academy of SciencesChina 49 works
  4. 4 Stanford UniversityUnited States 49 works
  5. 5 Design Intelligence (United States)United States 49 works
  6. 6 Helmholtz Association of German Research CentresGermany 46 works
  7. 7 National University of SingaporeSingapore 41 works
  8. 8 Georgia Institute of TechnologyUnited States 39 works
  9. 9 Tsinghua UniversityChina 39 works
  10. 10 SRM Institute of Science and TechnologyIndia 38 works

Who are the leading researchers in Explainable Artificial Intelligence (XAI)?

The most-cited researchers publishing on Explainable Artificial Intelligence (XAI) include David Moher, Yoshua Bengio and Robert John Tibshirani.

  1. 1 David Moher Canada 898k citations
  2. 2 Yoshua Bengio Canada 476k citations
  3. 3 Robert John Tibshirani United States 396k citations
  4. 4 Julian P. T. Higgins United Kingdom 390k citations
  5. 5 Steven L. Salzberg United States 372k citations
  6. 6 John P. A. Ioannidis United States 317k citations
  7. 7 Gregory Y.H. Lip United Kingdom 311k citations
  8. 8 Karl John Friston United Kingdom 310k citations
  9. 9 Trevor Hastie United States 301k citations
  10. 10 Martin McKee United Kingdom 270k 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 Explainable Artificial Intelligence (XAI)?

The most cited paper in Explainable Artificial Intelligence (XAI) is "Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization" (Ramprasaath R. Selvaraju, Michael Cogswell, Abhishek Kumar Das et al., 2017), with 23,064 citations. Next come ""Why Should I Trust You?"" (16,496) and "Visualizing and Understanding Convolutional Networks" (15,691).

Most cited papers
#PaperReleasedCitations
1 Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization Ramprasaath R. Selvaraju, Michael Cogswell, Abhishek Kumar Das et al. Conference paper Oct 2017 23,064
2 "Why Should I Trust You?" Marco Túlio Ribeiro, Sameer Kumar Singh, Carlos Guestrin Conference paper 8 Aug 2016 16,496
3 Visualizing and Understanding Convolutional Networks Matthew D. Zeiler, Rob Fergus · Lecture notes in computer science Conference paperOpen access 2014 15,691
4 Generative adversarial networks Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza et al. · Communications of the ACM 22 Oct 2020 14,417
5 On a Method to Measure Supervised Multiclass Model’s Interpretability: Application to Degradation Diagnosis (Short Paper) Gauriat, Charles-Maxime, Pencolé, Yannick, Ribot, Pauline et al. · OASIcs : OpenAccess Series in Informatics Conference paperOpen access 2024 13,571
All 99 most cited papers, with filters and sorting

Where is Explainable Artificial Intelligence (XAI) research done?

The largest centres of Explainable Artificial Intelligence (XAI) research in 2022-now are Beijing (China), London (United Kingdom), Chennai (India) and Seoul (South Korea). Among places with at least 20 works in it, it is an unusually large share of all research in Norman and Oldham.

Largest cities, 2022-now

  1. 1 BeijingChina 312 works
  2. 2 LondonUnited Kingdom 200 works
  3. 3 ChennaiIndia 132 works
  4. 4 SeoulSouth Korea 129 works
  5. 5 New YorkUnited States 127 works
  6. 6 ShanghaiChina 126 works
  7. 7 DhakaBangladesh 119 works
  8. 8 SingaporeSingapore 115 works
  9. 9 TokyoJapan 111 works
  10. 10 BengaluruIndia 101 works

Where it is the local speciality

  1. NormanUS · 55.4 works13×
  2. OldhamGB · 21.9 works11×
← less than its size predicts1×more →

Location quotient: how much more of its research is in Explainable Artificial Intelligence (XAI) than the world average.

See Explainable Artificial Intelligence (XAI) on the map

Where is the best place to study Explainable Artificial Intelligence (XAI)?

Among universities, judged by research, University of Oxford, Harvard University and Carnegie Mellon 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%10%20%30%mean 15.02%fractional works in this field (log) →share of work in the world top 10% →Harvard UniversityUniversity of OxfordUniversity College L…Carnegie Mellon Univ…
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 OxfordUnited Kingdom 69.217.8%2.1×33 +64.3%
2Harvard UniversityUnited States 68.518.6%1.0×38 +194.1%
3Carnegie Mellon UniversityUnited States 68.29.2%11.6×54 +50.3%
4University College LondonUnited Kingdom 67.717.5%1.8×32 +78.6%
5Stanford UniversityUnited States 66.211.2%3.0×49 +44.2%
6National University of SingaporeSingapore 66.211.3%3.0×41 +142.3%
7Delft University of TechnologyNetherlands 64.713.0%4.4×33 +230.9%
8University of WashingtonUnited States 63.013.3%2.5×33 +100.5%
9University of JyväskyläFinland 62.226.1%4.5×9 +139.0%
10Massachusetts Institute of TechnologyUnited States 62.012.2%4.2×33 +42.6%

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 Explainable Artificial Intelligence (XAI), country by country

Is Explainable Artificial Intelligence (XAI) research growing?

Output in 2022-2025 was 321% higher than in 2018-2021, peaking in 2026. The fastest-growing topics are Explainable Artificial Intelligence (XAI).

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 Explainable Artificial Intelligence (XAI) as a percentage of every work published that year, 0.038% in 2024.

still counting0.025%0.050%0.075%Explainable Artificial Intelligence (XAI)0.070% in 202519801990200020102020

Fractional works of Explainable Artificial Intelligence (XAI) 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%Explainable Artificial Intelligence (XAI)10.0% in 20252020

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 explainable AI research?

By volume in 2022-now, Centre National de la Recherche Scientifique publishes the most Explainable Artificial Intelligence (XAI) research, followed by Carnegie Mellon University and Chinese Academy of Sciences. By volume, the United States and China publish the most (3k and 1.6k works in 2022-now).

All 1,273 questions in the Question Catalogue

Discussion

Ask a question or share a note about Explainable Artificial Intelligence (XAI). Posts are plain text and can be reported.