Graph Transfer Learning

Graph Transfer Learning is a machine learning paradigm that enables the adaptation and application of knowledge acquired from a source graph domain to improve learning performance in a different but related target graph domain, thereby distinguishing itself from conventional graph learning methods through the explicit transfer of structural and feature-based patterns across non-identical graph distributions.

128

Publications

7.4K

Citations

511

Authors

201

Institutions

Publications per year

2017–2026

115

Authors

511

  1. RZ
    Rong Zhou

    Mississippi State University, United States

    5 publications · 264 citations

    5

    h-index

  2. NK
    Nesreen K. Ahmed

    Intel (United States), United States

    5 publications · 264 citations

    5

    h-index

  3. RA
    Ryan A. Rossi

    Adobe Systems (United States), United States

    5 publications · 264 citations

    5

    h-index

  4. AR
    Alejandro Ribeiro

    University of Pennsylvania, United States

    4 publications · 121 citations

    4

    h-index

  5. YF
    Yuan Fang

    Singapore Management University, Singapore

    4 publications · 279 citations

    4

    h-index

1–5 of 511

Venues

  1. arXiv (Cornell University)

    Repository · 19 publications · 2.1K citations

    16

    h-index

  2. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 6 publications · 268 citations

    6

    h-index

  3. IEEE Transactions on Knowledge and Data Engineering

    TKDE · 4 publications · 254 citations

    4

    h-index

  4. 4

    h-index

  5. 4

    h-index

1–5