World's Best Scientists 2026 revealed!

D-Index & Metrics

Computer Science

D-Index
53
Citations
12950
World Ranking
4769
National Ranking
2218

Overview

Kun Zhang is affiliated with Carnegie Mellon University in the United States and has contributed extensively to the field of computer science. Their research spans multiple subfields, notably artificial intelligence, computer vision and pattern recognition, management science and operations research, signal processing, and electrical and electronic engineering.

The scientist's publications cover a wide range of topics, including Bayesian modeling and causal inference, domain adaptation and few-shot learning, advanced graph neural networks, generative adversarial networks and image synthesis, anomaly detection techniques and applications, blind source separation techniques, and machine learning and data classification.

Kun Zhang has authored research articles published in high-profile venues such as:

  • DeepTrader: A Deep Reinforcement Learning Approach for Risk-Return Balanced Portfolio Management with Market Conditions Embedding (2021), Proceedings of the AAAI Conference on Artificial Intelligence
  • On the Role of Sparsity and DAG Constraints for Learning Linear DAGs (2020), arXiv (Cornell University)
  • A Causal View on Robustness of Neural Networks (2020), arXiv (Cornell University)
  • An Online Diagnosis Method for Sensor Intermittent Fault Based on Data-Driven Model (2022), IEEE Transactions on Power Electronics
  • Generative-Discriminative Complementary Learning (2020), Proceedings of the AAAI Conference on Artificial Intelligence

Frequent publication venues for their work include:

  • arXiv (Cornell University)
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • IEEE Transactions on Neural Networks and Learning Systems
  • ACM Transactions on Knowledge Discovery from Data
  • SSRN Electronic Journal

Collaborations have been an important aspect of Kun Zhang's research activities. Frequent coauthors include Biwei Huang, Ruichu Cai, Guangyi Chen, Mingming Gong, and Ignavier Ng.

Kun Zhang's research output demonstrates engagement with computational approaches that integrate learning theory, causal inference, and practical applications in intelligent systems and fault diagnosis. The scientist's work contributes to advancing methodologies in areas intersecting machine learning, signal processing, and artificial intelligence.

Best Publications

  • Identifying the Best Machine Learning Algorithms for Brain Tumor Segmentation, Progression Assessment, and Overall Survival Prediction in the BRATS Challenge

    Spyridon Bakas;Mauricio Reyes;Andras Jakab;Stefan Bauer

  • Inferring causation from time series in Earth system sciences

    Jakob Runge;Jakob Runge;Sebastian Bathiany;Erik Bollt;Gustau Camps-Valls

  • Review of Causal Discovery Methods Based on Graphical Models.

    Clark Glymour;Kun Zhang;Peter Spirtes

  • Deep Domain Generalization via Conditional Invariant Adversarial Networks

    Ya Li;Xinmei Tian;Mingming Gong;Yajing Liu

  • Multi-label learning by exploiting label dependency

    Min-Ling Zhang;Kun Zhang

  • Domain Adaptation under Target and Conditional Shift

    Kun Zhang;Bernhard Schlkopf;Krikamol Muandet;Zhikun Wang

  • Kernel-based conditional independence test and application in causal discovery

    Kun Zhang;Jonas Peters;Dominik Janzing;Bernhard Schölkopf

  • On causal and anticausal learning

    Dominik Janzing;Jonas Peters;Eleni Sgouritsa;Kun Zhang

  • Estimation of a Structural Vector Autoregression Model Using Non-Gaussianity

    Aapo Hyvärinen;Kun Zhang;Shohei Shimizu;Patrik O. Hoyer

  • On the identifiability of the post-nonlinear causal model

    Kun Zhang;Aapo Hyvärinen

  • Causal discovery and inference: concepts and recent methodological advances

    Peter Spirtes;Kun Zhang

  • Information-geometric approach to inferring causal directions

    Dominik Janzing;Joris Mooij;Kun Zhang;Jan Lemeire

  • On learning invariant representations for domain adaptation

    Han Zhao;Remi Tachet des Combes;Kun Zhang;Geoffrey J. Gordon;Geoffrey J. Gordon

  • Domain adaptation with conditional transferable components

    Mingming Gong;Kun Zhang;Tongliang Liu;Dacheng Tao

  • Geometry-Consistent Generative Adversarial Networks for One-Sided Unsupervised Domain Mapping

    Huan Fu;Mingming Gong;Chaohui Wang;Kayhan Batmanghelich

  • On Learning Invariant Representation for Domain Adaptation

    Han Zhao;Remi Tachet des Combes;Kun Zhang;Geoffrey J. Gordon

  • On Causal and Anticausal Learning

    Bernhard Schoelkopf;Dominik Janzing;Jonas Peters;Eleni Sgouritsa

  • Inferring deterministic causal relations

    Povilas Daniušis;Dominik Janzing;Joris Mooij;Jakob Zscheischler

  • Multi-source domain adaptation: a causal view

    Kun Zhang;Mingming Gong;Bernhard Scholkopf

  • Approximate Kernel-Based Conditional Independence Tests for Fast Non-Parametric Causal Discovery

    Eric V. Strobl;Kun Zhang;Shyam Visweswaran

  • Kernel-based Conditional Independence Test and Application in Causal Discovery

    Kun Zhang;Jonas Peters;Dominik Janzing;Bernhard Schoelkopf

Frequent Co-Authors

Clark Glymour
Clark Glymour Carnegie Mellon University
Bernhard Schölkopf
Bernhard Schölkopf Max Planck Institute for Intelligent Systems
Dacheng Tao
Dacheng Tao Nanyang Technological University
Dominik Janzing
Dominik Janzing Amazon (United States)
Aapo Hyvärinen
Aapo Hyvärinen University of Helsinki
Tongliang Liu
Tongliang Liu University of Sydney
Jakob Zscheischler
Jakob Zscheischler Helmholtz Centre for Environmental Research
Peter Spirtes
Peter Spirtes Carnegie Mellon University
Jiuyong Li
Jiuyong Li University of South Australia
Tom Vercauteren
Tom Vercauteren King's College London

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

Report an issue

We appreciate your kind effort to assist us to improve this page, it would be helpful providing us with as much detail as possible in the text box below:

Related Online Degrees & Career Pathways

Choosing to study Computer Science in the USA opens doors to a wide range of career pathways. In today's digital age, online learning options make it easier to find programs that fit your schedule and career goals. If you're looking to fast-track your education, exploring a fastest computer science degree can help you enter the workforce sooner.

For those interested in interdisciplinary careers, considering related fields can also be an excellent option. Studying for an environmental science degree can open up roles in sustainability, tech-driven environmental solutions, and policy development. Alternatively, the demand for technical expertise is growing in engineering fields such as mechanical and environmental engineering.

Cost is a key consideration for many students. If affordability is a top concern, you may want to look into the cheapest online environmental science degree or pursue an online mechanical engineering degree to find budget-friendly options that still offer excellent education and career prospects. These related online degrees broaden the scope of opportunities available in STEM and beyond.

Best Scientists Citing Kun Zhang

Trending Scientists

Recently Published Articles