Mind the Gap: Mitigating the Distribution Gap in Graph Few-shot Learning
Mind the Gap: Mitigating the Distribution Gap in Graph Few-shot Learning
复制标题
DOI：
--
复制
发表时间：
--
期刊：
影响因子：
--
通讯作者：
中科院分区：
文献类型：
--
作者：
目前流行的监督式深度图学习模型经常受到标签稀缺问题的困扰，导致在有限的注释数据面前性能下降。尽管已经开发了许多图少拍学习（GFL）方法来缓解这个问题，但它们往往过度依赖于标记数据。这种对标记数据的过度依赖会导致测试阶段由于分布间隙的存在而削弱泛化能力。此外，现有的GFL方法缺乏通用性，因为它们的设计与任务或数据特定的特征相结合。为了解决这些缺点，我们提出了一个新的S elf-D istilled G F ew-shot L学习框架（SDGFL），这是通用的和有效的。SDGFL利用自我提炼的对比学习程序来提高GFL。具体来说，我们的模型首先使用未标记数据通过对比学习预训练图形编码器。然后，将训练好的编码器冻结为教师模型，以提取具有对比损失的学生模型。然后将蒸馏后的模型送入GFL。SDGFL通过以自监督的方式学习数据表示，有效地缓解了分布差距，增强了泛化能力。此外，我们提出的框架是任务和数据独立的，使其成为通用的图形挖掘的目的的通用工具。为了评估我们提出的框架的有效性，我们引入了一个基于信息的测量，量化其能力。通过全面的实验，我们证明了SDGFL在少数情况下跨多个数据集的各种图挖掘任务上优于最先进的基线。与现有方法相比，我们还提供了SDGFL的上级性能的定量测量
Prevailing supervised deep graph learning models often suffer from the issue of label scarcity, leading to performance degradation in the face of limited annotated data. Although numerous graph few-shot learning (GFL) methods have been developed to mitigate this problem, they tend to rely excessively on labeled data. This over-reliance on labeled data can result in impaired generalization ability in the test phase due to the existence of a distribution gap . Moreover, existing GFL methods lack a general purpose as their designs are coupled with task or data-specific characteristics. To address these shortcomings, we propose a novel S elf- D istilled G raph F ew-shot L earning framework (SDGFL) that is both general and effective. SDGFL leverages a self-distilled contrastive learning procedure to boost GFL. Specifically, our model first pre-trains a graph encoder with contrastive learning using unlabeled data. Later, the trained encoder is frozen as a teacher model to distill a student model with a contrastive loss. The distilled model is then fed to GFL. By learning data representation in a self-supervised manner, SDGFL effectively mitigates the distribution gap and enhances generalization ability. Furthermore, our proposed framework is task and data-independent, making it a versatile tool for general graph mining purposes. To evaluate the effectiveness of our proposed framework, we introduce an information-based measurement that quantifies its capability. Through comprehensive experiments, we demonstrate that SDGFL outperforms state-of-the-art baselines on various graph mining tasks across multiple datasets in the few-shot scenario. We also provide a quantitative measurement of SDGFL’s superior performance in comparison to existing methods