What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Computer network
Artificial intelligence, Machine learning, Collaborative filtering, Global Positioning System and Graph embedding are his primary areas of study.
In the field of Artificial intelligence, his study on Hidden Markov model, Feature vector, Similarity and Categorization overlaps with subjects such as Disjoint sets.
His Machine learning study combines topics from a wide range of disciplines, such as Learning methods, Zero shot learning, Focus and Adaptation.
Vincent W. Zheng interconnects Ubiquitous computing and Mobile computing in the investigation of issues within Global Positioning System.
His Graph embedding study incorporates themes from Theoretical computer science and Computation.
His study in Data mining is interdisciplinary in nature, drawing from both Data modeling and Social network.
His most cited work include:
- A Comprehensive Survey of Graph Embedding: Problems, Techniques, and Applications (711 citations)
- Collaborative location and activity recommendations with GPS history data (584 citations)
- Modeling User Activity Preference by Leveraging User Spatial Temporal Characteristics in LBSNs (262 citations)
What are the main themes of his work throughout his whole career to date?
Vincent W. Zheng mainly investigates Artificial intelligence, Machine learning, Theoretical computer science, Embedding and Data mining.
When carried out as part of a general Artificial intelligence research project, his work on Activity recognition and Artificial neural network is frequently linked to work in Knowledge transfer, Domain and Set, therefore connecting diverse disciplines of study.
As a part of the same scientific family, Vincent W. Zheng mostly works in the field of Machine learning, focusing on Hidden Markov model and, on occasion, Data modeling.
As part of the same scientific family, Vincent W. Zheng usually focuses on Theoretical computer science, concentrating on Graph embedding and intersecting with Computation and Graph drawing.
His Data mining research includes themes of Feature extraction, Ranking and Social network.
As a member of one scientific family, Vincent W. Zheng mostly works in the field of Social network, focusing on Content distribution and, on occasion, Collaborative filtering.
He most often published in these fields:
- Artificial intelligence (28.42%)
- Machine learning (23.16%)
- Theoretical computer science (18.95%)
What were the highlights of his more recent work (between 2019-2021)?
- World Wide Web (9.47%)
- Recommender system (8.42%)
- Collaborative filtering (11.58%)
In recent papers he was focusing on the following fields of study:
Vincent W. Zheng spends much of his time researching World Wide Web, Recommender system, Collaborative filtering, Node and Embedding.
His study in the field of Social media is also linked to topics like Performance improvement.
His studies in Recommender system integrate themes in fields like Categorization, Partition and Feature vector.
His work carried out in the field of Collaborative filtering brings together such families of science as Social network, Content distribution and Personalization.
His work focuses on many connections between Embedding and other disciplines, such as Scalability, that overlap with his field of interest in Theoretical computer science.
His Theoretical computer science research is multidisciplinary, incorporating perspectives in Artificial neural network, Structure and Bipartite graph.
Between 2019 and 2021, his most popular works were:
- Adam revisited: a weighted past gradients perspective (8 citations)
- Electricity Theft Pinpointing Through Correlation Analysis of Master and Individual Meter Readings (7 citations)
- Metagraph-Based Learning on Heterogeneous Graphs (7 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Computer network
His scientific interests lie mostly in Consumption, Correlation analysis, Energy supply, Computer security and Energy consumption.
His Consumption investigation overlaps with Electricity and Metre.
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.
