Graph geometry interaction learning
File version
Version of Record (VoR)
Author(s)
Pan, S
Zhou, C
Wu, J
Cao, Y
Wang, B
Griffith University Author(s)
Primary Supervisor
Other Supervisors
Editor(s)
Date
Size
File type(s)
Location
Vancouver, Canada
License
Abstract
While numerous approaches have been developed to embed graphs into either Euclidean or hyperbolic spaces, they do not fully utilize the information available in graphs, or lack the flexibility to model intrinsic complex graph geometry. To utilize the strength of both Euclidean and hyperbolic geometries, we develop a novel Geometry Interaction Learning (GIL) method for graphs, a well-suited and efficient alternative for learning abundant geometric properties in graph. GIL captures a more informative internal structural features with low dimensions while maintaining conformal invariance of each space. Furthermore, our method endows each node the freedom to determine the importance of each geometry space via a flexible dual feature interaction learning and probability assembling mechanism. Promising experimental results are presented for five benchmark datasets on node classification and link prediction tasks.
Journal Title
Conference Title
Advances in Neural Information Processing Systems 33 (NeurIPS 2020)
Book Title
Edition
Volume
2020-December
Issue
Thesis Type
Degree Program
School
DOI
Patent number
Funder(s)
Grant identifier(s)
Rights Statement
Rights Statement
© The Author(s) 2020. The attached file is reproduced here in accordance with the copyright policy of the publisher. For information about this conference please refer to the conference’s website or contact the author(s).
Item Access Status
Note
Access the data
Related item(s)
Subject
Applied and developmental psychology
Cognitive and computational psychology
Machine learning
Persistent link to this record
Citation
Zhu, S; Pan, S; Zhou, C; Wu, J; Cao, Y; Wang, B, Graph geometry interaction learning, Advances in Neural Information Processing Systems 33 (NeurIPS 2020), 2020