.png){kind=icon}
Return
Improving Augmentation Consistency for Graph Contrastive Learning
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2023.110182.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Graph contrastive learning (GCL) enhances unsupervised graph representation by generating different con-trastive views, in which properties of augmented nodes are required to be aligned with their anchors. However, we find that in some existing GCL methods, it is hard to inherit semantic and structural properties of graphs from anchor views due to inconsistent augmentation schemes, which may hurt node consistency in augmented views. In this paper, we present ConGCL to improve node consistency and enhance node classification. Specifically, we first consider context entailment, which integrates the semantic and structural properties to better mine the underlying consistency relationships of nodes. Beneficial from this, we then design a novel consistency improvement loss to maintain augmentation consistency agreement among positive node pairs under stochastic augmentation schemes. To investigate the effectiveness of ConGCL on improving augmentation consistency and enhancing node classification, we conduct empirical study and extensive experiments on benchmark datasets. The code is available at: https://github.com/brysonwx/ConGCL.
Keywords:
Graph contrastive learning
Augmentation consistency
Journal
IF:
7.6
Papers:
1.3W
Citations:
4.5W
Organization
Cited Papers
Can CD34 discriminate between benign and malignant hepatocytic lesions in fine-needle aspirates and thin core biopsies?.png)
Cancer
OAAI
CancerIF0
OAAIShareSaveAccessibility Disruptions in the Context of Flooding, Fragile Infrastructure and Climate Change
PREAI
ShareSaveTriplet teaching graph contrastive networks with self-evolving adaptive augmentationPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
ShareSaveDoubly contrastive representation learning for federated image recognitionPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
ShareSaveValidity and Psychometric Properties of Malay Translated Religious Orientation Scale-Revised among Malaysian Adult SamplesAkademika
OAAI
AkademikaIF0
OAAIShareSaveShareSaveTechnical and Technological Innovations and Quality in Road transport of Goods - Selected AspectsOAAI
OAAIShareSave
View more