面向基于图的半监督学习的伪对比学习
Pseudo Contrastive Learning for Graph-based Semi-supervised Learning
AI总结：
针对半监督图神经网络中伪标签质量不佳的问题，提出伪对比学习框架，将生成伪标签转化为识别可靠负样本对，结合拓扑加权对比损失，在五个真实图数据集上提升了多种GNN的性能。
摘要：
伪标记是一种通过基于高置信度预测生成额外伪标签来提升半监督图神经网络（GNNs）性能的技术。但由于分类目标对给定标签的敏感性，生成的伪标签的质量一直是长期存在的问题。为了避免指示“某个节点属于特定类别”的不可靠分类监督，我们更倾向于采用容错性更强的对比监督，即表明“两个节点不属于同一类别”。由此，生成高质量伪标签的问题被转化为一个更宽松的版本：识别可靠的负样本对。为实现这一目标，我们提出了一种适用于图神经网络的通用框架，名为Pseudo Contrastive Learning（PCL，伪对比学习）。该框架会将正伪标签和负伪标签指向同一类别的两个节点分开。为了将拓扑知识融入学习过程，我们设计了一种拓扑加权对比损失，它会投入更多精力来分离拓扑距离更小的负样本对。在实验中，我们将PCL应用于多种图神经网络，在五个真实世界图数据集上，其性能始终优于采用其他流行通用技术的同类模型。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
