Johannes Klicpera
- Artificial Intelligence top 10%
- Advanced Graph Neural Networks 6
- Advanced Text Analysis Techniques 1
-
- Complex Network Analysis Techniques 3
-
- Computational Drug Discovery Methods 2
-
- Recommender Systems and Techniques 2
-
- Machine Learning in Materials Science 2
-
- Protein Structure and Dynamics 1
-
- Functional Brain Connectivity Studies 1
- Co-authors
- Stephan GünnemannAleksandar Bojchevski
- Cited by
- Artificial IntelligenceStatistical and Nonlinear PhysicsComputational Theory and Mathematics
- Journals
- mediaTUM (Technical University of Munich) (1 paper)arXiv (Cornell University) (8 papers)
- Partner nations
- Germany
In The Last Decade
Johannes Klicpera
9 papers receiving 272 citations
Peers
Comparison fields: 5 of 54
- Artificial Intelligence 196
- Statistical and Nonlinear Physics 70
- Computational Theory and Mathematics 47
- Computer Vision and Pattern Recognition 50
- Information Systems 40
Countries citing papers authored by Johannes Klicpera
This map shows the geographic impact of Johannes Klicpera's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Johannes Klicpera with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Johannes Klicpera more than expected).
Fields of papers citing papers by Johannes Klicpera
This network shows the impact of papers produced by Johannes Klicpera. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Johannes Klicpera. The network helps show where Johannes Klicpera may publish in the future.
Co-authorship network
The 2 scholars most cited alongside Johannes Klicpera, linked wherever they have co-authored with each other. Click a name or a connecting line to browse the papers they share.
All Works
| # | Work | ||
|---|---|---|---|
| 1 | 2023 | 1 | |
| 2 | Directional Message Passing on Molecular Graphs via Synthetic Coordinates | 2021 | 5 |
| 3 | Scalable Optimal Transport in High Dimensions for Graph Distances, Embedding Alignment, and More | 2021 | 3 |
| 4 | Directional Message Passing for Molecular Graphs | 2020 | 74 |
| 5 | Diffusion Improves Graph Learning | 2019 | 34 |
| 6 | Combining Neural Networks with Personalized PageRank for Classification on Graphs | 2018 | 31 |
| 7 | Predict then Propagate: Combining neural networks with personalized pagerank for classification on graphs | 2018 | 3 |
| 8 | Predict then Propagate: Graph Neural Networks meet Personalized PageRank | 2018 | 122 |
| 9 | Personalized Embedding Propagation: Combining Neural Networks on Graphs with Personalized PageRank. | 2018 | 7 |
About Johannes Klicpera
Johannes Klicpera is a scholar working on Statistical and Nonlinear Physics, Artificial Intelligence and Computational Theory and Mathematics, having authored 9 papers that have together received 280 indexed citations. Recurring topics across this work include Advanced Graph Neural Networks (6 papers), Complex Network Analysis Techniques (3 papers), Recommender Systems and Techniques (2 papers), Machine Learning in Materials Science (2 papers), Computational Drug Discovery Methods (2 papers), Advanced Text Analysis Techniques (1 paper), Protein Structure and Dynamics (1 paper) and Functional Brain Connectivity Studies (1 paper). The work is most often cited by research in Artificial Intelligence (196 citations), Statistical and Nonlinear Physics (70 citations) and Computational Theory and Mathematics (47 citations). Johannes Klicpera has collaborated with scholars based in Germany. Frequent co-authors include Stephan Günnemann and Aleksandar Bojchevski. Their work appears in journals such as mediaTUM (Technical University of Munich) and arXiv (Cornell University).
Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive bibliographic database. While OpenAlex provides broad and valuable coverage of the global research landscape, it—like all bibliographic datasets—has inherent limitations. These include incomplete records, variations in author disambiguation, differences in journal indexing, and delays in data updates. As a result, some metrics and network relationships displayed in Rankless may not fully capture the entirety of a scholar's output or impact.