What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- The Internet
His primary areas of investigation include Data mining, Theoretical computer science, Social network, World Wide Web and Graph.
Jure Leskovec has researched Data mining in several fields, including Cluster analysis, Information cascade, Set, Community structure and Robustness.
His Theoretical computer science study combines topics in areas such as Complex system, Feature learning, Artificial intelligence and Graph.
His Social network research is multidisciplinary, relying on both Variation, Social psychology, Social psychology, Friendship and The Internet.
The study incorporates disciplines such as Node, Usability, Data science and Telecommunications network in addition to World Wide Web.
His Graph research incorporates elements of Machine learning and Pharmacogenomics.
His most cited work include:
- node2vec: Scalable Feature Learning for Networks (4249 citations)
- Inductive Representation Learning on Large Graphs (2132 citations)
- Friendship and mobility: user movement in location-based social networks (2066 citations)
What are the main themes of his work throughout his whole career to date?
Jure Leskovec mostly deals with Artificial intelligence, Theoretical computer science, Graph, Machine learning and World Wide Web.
His Artificial intelligence research incorporates themes from Structure, Pattern recognition and Natural language processing.
His studies in Theoretical computer science integrate themes in fields like Graph, Embedding, Inference, Feature learning and Node.
His study of Graph neural networks is a part of Graph.
His research related to Social network and Recommender system might be considered part of World Wide Web.
The Social network study combines topics in areas such as Social media, Data mining and Information cascade.
He most often published in these fields:
- Artificial intelligence (23.48%)
- Theoretical computer science (21.96%)
- Graph (15.65%)
What were the highlights of his more recent work (between 2019-2021)?
- Artificial intelligence (23.48%)
- Theoretical computer science (21.96%)
- Machine learning (14.57%)
In recent papers he was focusing on the following fields of study:
Jure Leskovec spends much of his time researching Artificial intelligence, Theoretical computer science, Machine learning, Graph and Graph.
In general Artificial intelligence study, his work on Deep learning often relates to the realm of Function, thereby connecting several areas of interest.
His studies deal with areas such as Embedding, Graph neural networks, Feature learning, Node and Computation as well as Theoretical computer science.
His work deals with themes such as Structure, Scalability, Task and Benchmark, which intersect with Machine learning.
His Graph research includes elements of Artificial neural network, Regularization, Algorithm and Message passing.
His Graph study combines topics from a wide range of disciplines, such as Missing data, Imputation, Strong prior, Heuristics and Bipartite graph.
Between 2019 and 2021, his most popular works were:
- Mobility network models of COVID-19 explain inequities and inform reopening. (184 citations)
- Open Graph Benchmark: Datasets for Machine Learning on Graphs (136 citations)
- Strategies for Pre-training Graph Neural Networks (79 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- The Internet
His scientific interests lie mostly in Theoretical computer science, Graph, Artificial intelligence, Machine learning and Graph.
Jure Leskovec performs multidisciplinary studies into Theoretical computer science and Vector space in his work.
Jure Leskovec has included themes like Artificial neural network and Computation in his Graph study.
His work on Deep learning and Data point as part of general Artificial intelligence research is often related to Training, thus linking different fields of science.
His Machine learning research incorporates elements of Biological network and Benchmark.
His Graph study integrates concerns from other disciplines, such as Feature learning, Training set, Shortest path problem and PageRank.
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.
