Keyulu Xu
- Artificial Intelligence top 10%
- Computer Vision and Pattern Recognition
- Statistical and Nonlinear Physics top 10%
- Information Systems
- Molecular Biology
- Co-authors
- Stefanie JegelkaKen‐ichi KawarabayashiYonglong TianTomohiro SonobeChengtao LiMozhi ZhangSimon S. DuJordan Boyd‐Graber
- Topics
- Advanced Graph Neural Networks (6 papers)Explainable Artificial Intelligence (XAI) (2 papers)Machine Learning in Materials Science (2 papers)
- Cited by
- Artificial IntelligenceStatistical and Nonlinear PhysicsComputer Vision and Pattern Recognition
- Journals
- arXiv (Cornell University)International Conference on Machine LearningInternational Conference on Learning Representations
- Partner nations
- United StatesJapanUnited Kingdom
In The Last Decade
Keyulu Xu
7 papers receiving 179 citations
Peers
Comparison fields: 5 of 32
- Artificial Intelligence 173
- Computer Vision and Pattern Recognition 53
- Statistical and Nonlinear Physics 46
- Information Systems 23
- Molecular Biology 20
Countries citing papers authored by Keyulu Xu
This map shows the geographic impact of Keyulu Xu'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 Keyulu Xu with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Keyulu Xu more than expected).
Fields of papers citing papers by Keyulu Xu
This network shows the impact of papers produced by Keyulu Xu. 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 Keyulu Xu. The network helps show where Keyulu Xu may publish in the future.
Co-authorship network of co-authors of Keyulu Xu
This figure shows the co-authorship network connecting the top 25 collaborators of Keyulu Xu. A scholar is included among the top collaborators of Keyulu Xu based on the total number of citations received by their joint publications. Widths of edges represent the number of papers authors have co-authored together. Node borders signify the number of papers an author published with Keyulu Xu. Keyulu Xu is excluded from the visualization to improve readability, since they are connected to all nodes in the network.
All Works
| # | Work | Indexed citations |
|---|---|---|
| 1 | How Neural Networks Extrapolate: From Feedforward to Graph Neural Networks | 6 |
| 2 | Information Obfuscation of Graph Neural Networks | 0 |
| 3 | GraphNorm: A Principled Approach to Accelerating Graph Neural Network Training | 1 |
| 4 | Graph Adversarial Networks: Protecting Information against Adversarial Attacks | 2 |
| 5 | What Can Neural Networks Reason About | 11 |
| 6 | Graph Neural Tangent Kernel: Fusing Graph Neural Networks with Graph Kernels | 16 |
| 7 | 23 | |
| 8 | Representation Learning on Graphs with Jumping Knowledge Networks | 131 |
About Keyulu Xu
Keyulu Xu is a scholar working on Artificial Intelligence, Computer Vision and Pattern Recognition and Statistical and Nonlinear Physics, having authored 8 papers that have together received 190 indexed citations. Recurring topics across this work include Advanced Graph Neural Networks (6 papers), Explainable Artificial Intelligence (XAI) (2 papers) and Machine Learning in Materials Science (2 papers). The work is most often cited by research in Artificial Intelligence (173 citations), Statistical and Nonlinear Physics (46 citations) and Computer Vision and Pattern Recognition (53 citations). Keyulu Xu has collaborated with scholars based in United States, Japan and United Kingdom. Frequent co-authors include Stefanie Jegelka, Ken‐ichi Kawarabayashi, Yonglong Tian, Tomohiro Sonobe, Chengtao Li, Mozhi Zhang, Simon S. Du, Jordan Boyd‐Graber, Barnabás Póczos and Kangcheng Hou. Their work appears in journals such as arXiv (Cornell University), International Conference on Machine Learning and International Conference on Learning Representations.
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.