Augmentations in Hypergraph Contrastive Learning: Fabricated and Generative
This paper targets at improving the generalizability of hypergraph neural networks in the low-label regime, through applying the contrastive learning approach from images/graphs (we refer to it as ). We focus on the following question: We provide the solutions in two folds. First, guided by domain k...
Saved in:
Published in | Advances in neural information processing systems Vol. 35; p. 1909 |
---|---|
Main Authors | , , , , , |
Format | Journal Article |
Language | English |
Published |
United States
01.12.2022
|
Online Access | Get more information |
ISSN | 1049-5258 |
Cover
Loading…