HAT-GAE: Self-supervised graph autoencoders with hierarchical adaptive masking and trainable corruption

Chengyu Sun; Liang Hu; Hongtu Li; Shuai Li; Tuohang Li; Ling Chi

doi:10.1016/j.knosys.2023.110920

ScienceGate Book Chapters

JOURNAL ARTICLE

HAT-GAE: Self-supervised graph autoencoders with hierarchical adaptive masking and trainable corruption

Chengyu Sun Liang Hu Hongtu Li Shuai Li Tuohang Li Ling Chi

Year: 2023 Journal: Knowledge-Based Systems Vol: 279 Pages: 110920-110920 Publisher: Elsevier BV

DOI: 10.1016/j.knosys.2023.110920

Get Full-Text PDF Get Analytical Report

Keywords:

Computer science Autoencoder Artificial intelligence Graph Feature learning Machine learning Robustness (evolution) Masking (illustration) Pairwise comparison Pattern recognition (psychology) Deep learning Theoretical computer science

Metrics

Cited By

1.02

FWCI (Field Weighted Citation Impact)

Refs

0.76

Citation Normalized Percentile

Is in top 1%

Is in top 10%

Citation History

Topics

Advanced Graph Neural Networks

Physical Sciences → Computer Science → Artificial Intelligence

Topic Modeling

Physical Sciences → Computer Science → Artificial Intelligence

Domain Adaptation and Few-Shot Learning

Physical Sciences → Computer Science → Artificial Intelligence

HAT-GAE: Self-supervised graph autoencoders with hierarchical adaptive masking and trainable corruption

Metrics

Citation History

Topics

Related Documents

S2GAE: Self-Supervised Graph Autoencoders are Generalizable Learners with Graph Masking

GraphMAE: Self-Supervised Masked Graph Autoencoders

Self-supervised graph learning with target-adaptive masking for session-based recommendation

Graph Positional Autoencoders as Self-supervised Learners

Evolved Hierarchical Masking for Self-Supervised Learning