H-Index & Metrics Top Publications

H-Index & Metrics

Discipline name H-index Citations Publications World Ranking National Ranking
Computer Science H-index 35 Citations 5,659 147 World Ranking 5982 National Ranking 287

Overview

What is he best known for?

The fields of study he is best known for:

  • Artificial intelligence
  • Machine learning
  • Statistics

His scientific interests lie mostly in Artificial intelligence, Data mining, Cluster analysis, Graph and Theoretical computer science. His work deals with themes such as Machine learning and Computation, which intersect with Artificial intelligence. The concepts of his Data mining study are interwoven with issues in Correlation clustering and Fuzzy clustering.

Stephan Günnemann is studying Clustering high-dimensional data, which is a component of Cluster analysis. His study looks at the relationship between Graph and topics such as Algorithm, which overlap with Attack model, Spectral clustering and Spectral method. His Theoretical computer science research incorporates elements of Adversarial system, Embedding, Representation, Ranking and Random walk.

His most cited work include:

  • Adversarial Attacks on Neural Networks for Graph Data (220 citations)
  • Evaluating clustering in subspace projections of high dimensional data (190 citations)
  • Pitfalls of Graph Neural Network Evaluation. (185 citations)

What are the main themes of his work throughout his whole career to date?

Stephan Günnemann mainly investigates Artificial intelligence, Data mining, Theoretical computer science, Graph and Cluster analysis. He has researched Artificial intelligence in several fields, including Machine learning and Pattern recognition. His Data mining research is multidisciplinary, incorporating perspectives in Scalability, Multivariate statistics and Tracing.

His Theoretical computer science research is multidisciplinary, incorporating elements of Adversarial system, Graph, Structure, Computation and Random walk. Stephan Günnemann has included themes like Artificial neural network, Computational complexity theory, Algorithm and PageRank in his Graph study. Stephan Günnemann combines subjects such as Subspace topology and Linear subspace with his study of Cluster analysis.

He most often published in these fields:

  • Artificial intelligence (38.25%)
  • Data mining (30.60%)
  • Theoretical computer science (24.59%)

What were the highlights of his more recent work (between 2019-2021)?

  • Artificial intelligence (38.25%)
  • Algorithm (12.57%)
  • Robustness (13.66%)

In recent papers he was focusing on the following fields of study:

Stephan Günnemann mostly deals with Artificial intelligence, Algorithm, Robustness, Theoretical computer science and Graph. His Artificial intelligence study integrates concerns from other disciplines, such as Machine learning, Code and Natural language processing. His Robustness research includes elements of Smoothing, Feature and Semi-supervised learning.

The study incorporates disciplines such as Relational database, Graph and Scaling in addition to Theoretical computer science. His research in the fields of Graph neural networks overlaps with other disciplines such as Scene graph. His work on Graph neural networks is being expanded to include thematically relevant topics such as Data mining.

Between 2019 and 2021, his most popular works were:

  • Directional Message Passing for Molecular Graphs (54 citations)
  • Scaling Graph Neural Networks with Approximate PageRank (24 citations)
  • Directional Message Passing for Molecular Graphs (15 citations)

In his most recent research, the most cited papers focused on:

  • Artificial intelligence
  • Statistics
  • Machine learning

Stephan Günnemann mainly focuses on Graph, Theoretical computer science, Algorithm, Message passing and Artificial neural network. The Graph study combines topics in areas such as Graph and Artificial intelligence. His research integrates issues of Basis and Natural language processing in his study of Artificial intelligence.

His studies deal with areas such as Relational database, Graph neural networks and Scaling as well as Theoretical computer science. His biological study spans a wide range of topics, including Equivariant map and Topology. His Artificial neural network study incorporates themes from Calibration, Uncertainty quantification, Inference, Posterior probability and Dropout.

This overview was generated by a machine learning system which analysed the scientist’s body of work. If you have any feedback, you can contact us here.

Top Publications

Pitfalls of Graph Neural Network Evaluation.

Oleksandr Shchur;Maximilian Mumme;Aleksandar Bojchevski;Stephan Günnemann.
arXiv: Learning (2018)

385 Citations

Evaluating clustering in subspace projections of high dimensional data

Emmanuel Müller;Stephan Günnemann;Ira Assent;Thomas Seidl.
very large data bases (2009)

338 Citations

Adversarial Attacks on Neural Networks for Graph Data

Daniel Zügner;Amir Akbarnejad;Stephan Günnemann.
knowledge discovery and data mining (2018)

286 Citations

Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Ranking

Aleksandar Bojchevski;Stephan Günnemann.
international conference on learning representations (2018)

257 Citations

Predict then Propagate: Graph Neural Networks meet Personalized PageRank

Johannes Klicpera;Aleksandar Bojchevski;Stephan Günnemann.
international conference on learning representations (2018)

188 Citations

Adversarial Attacks on Graph Neural Networks via Meta Learning

Daniel Zügner;Stephan Günnemann.
international conference on learning representations (2019)

176 Citations

On Using Class-Labels in Evaluation of Clusterings

Ines Färber;Stephan Günnemann;Hans-Peter Kriegel;Peer Kröger.
(2010)

142 Citations

Subspace Clustering Meets Dense Subgraph Mining: A Synthesis of Two Paradigms

Stephan Gunnemann;Ines Farber;Brigitte Boden;Thomas Seidl.
international conference on data mining (2010)

136 Citations

Introduction to Tensor Decompositions and their Applications in Machine Learning.

Stephan Rabanser;Oleksandr Shchur;Stephan Günnemann.
arXiv: Machine Learning (2017)

133 Citations

Directional Message Passing for Molecular Graphs

Johannes Klicpera;Janek Groß;Stephan Günnemann.
international conference on learning representations (2020)

133 Citations

Profile was last updated on December 6th, 2021.
Research.com Ranking is based on data retrieved from the Microsoft Academic Graph (MAG).
The ranking h-index is inferred from publications deemed to belong to the considered discipline.

If you think any of the details on this page are incorrect, let us know.

Contact us

Top Scientists Citing Stephan Günnemann

Christos Faloutsos

Christos Faloutsos

Carnegie Mellon University

Publications: 39

Thomas Seidl

Thomas Seidl

Ludwig-Maximilians-Universität München

Publications: 27

Jiliang Tang

Jiliang Tang

Michigan State University

Publications: 27

Jure Leskovec

Jure Leskovec

Stanford University

Publications: 24

Arthur Zimek

Arthur Zimek

University of Southern Denmark

Publications: 22

Junzhou Huang

Junzhou Huang

The University of Texas at Arlington

Publications: 19

Leman Akoglu

Leman Akoglu

Carnegie Mellon University

Publications: 19

Peng Cui

Peng Cui

Tsinghua University

Publications: 18

Michael M. Bronstein

Michael M. Bronstein

Imperial College London

Publications: 18

Charu C. Aggarwal

Charu C. Aggarwal

IBM (United States)

Publications: 18

Philip S. Yu

Philip S. Yu

University of Illinois at Chicago

Publications: 18

Chuan Shi

Chuan Shi

Beijing University of Posts and Telecommunications

Publications: 17

Jie Tang

Jie Tang

Tsinghua University

Publications: 16

Suhang Wang

Suhang Wang

Pennsylvania State University

Publications: 16

Wenwu Zhu

Wenwu Zhu

Tsinghua University

Publications: 15

Something went wrong. Please try again later.