.png){kind=icon}
.png){kind=icon}
Return
Pseudo Contrastive Learning for graph-based semi-supervised learning
.png){kind=icon}
OA
AI
DOI：10.1016/j.neucom.2025.129375.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Pseudo Labeling is a technique used to improve the performance of semi-supervised Graph Neural Networks (GNNs) by generating additional pseudo-labels based on confident predictions. However, the quality of generated pseudo-labels has been a longstanding concern due to the sensitivity of the classification objective with respect to the given labels. To avoid the untrustworthy classification supervision indicating anode belongs to a specific class, we favor the fault-tolerant contrasting supervision demonstrating two nodes do not belong to the same class. Thus, the problem of generating high-quality pseudo-labels is then transformed into a relaxed version, i.e ., identifying reliable negative pairs. To achieve this, we propose a general framework for GNNs, termed Pseudo Contrastive Learning (PCL). It separates two nodes whose positive and negative pseudo- labels target the same class. To incorporate topological knowledge into learning, we devise a topologically weighted contrastive loss that spends more effort separating negative pairs with smaller topological distances. Experimentally, we apply PCL to various GNNs, which consistently outperform their counterparts using other popular general techniques on five real-world graphs.
Keywords:
Contrastive Learning
Pseudo Labeling
Node classification
Graph-based semi-supervised learning
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
6.5
Papers:
2.5W
Citations:
6.5W