Pseudo Contrastive Learning for Graph-based Semi-supervised Learning
This work addresses a specific bottleneck in graph-based semi-supervised learning for researchers and practitioners, offering an incremental improvement over existing pseudo-labeling techniques.
The paper tackles the problem of low-quality pseudo-labels in semi-supervised graph neural networks by proposing Pseudo Contrastive Learning (PCL), which transforms label generation into identifying reliable negative pairs and uses a topologically weighted contrastive loss, resulting in consistent performance improvements across various GNNs on five real-world graphs.
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 ``a node 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.