Contrastive Meta-Learning for Few-shot Node Classification
Contrastive Meta-Learning for Few-shot Node Classification
复制标题
DOI：
10.1145/3580305.3599288
复制
发表时间：
2023-06
期刊：
影响因子：
--
通讯作者：
Song Wang;Zhen Tan;Huan Liu;Jundong Li
中科院分区：
文献类型：
--
作者：
Song Wang;Zhen Tan;Huan Liu;Jundong Li
少样本节点分类旨在仅以有限的标记节点为参考来预测图中节点的标签，这在现实世界的图挖掘任务中具有重要意义。为了解决这种标签短缺的问题，现有的工作通常利用元学习框架，该框架利用多个情节从具有大量标记节点的类别中提取可迁移的知识，并将这些知识推广到具有有限标记节点的其他类别。从本质上讲，少样本节点分类的主要目的是学习可在不同类别之间通用的节点嵌入。为了实现这一目标，图神经网络（GNN）编码器必须能够区分不同类别之间的节点嵌入，同时还要对同一类别中的节点嵌入进行对齐。因此，在这项工作中，我们建议同时考虑模型的类内和类间通用性。我们在图上创建了一个新颖的对比式元学习框架，名为COSMIC，它有两个关键设计。首先，我们建议通过在每个情节中引入对比式两步优化来增强类内通用性，以明确地对齐同一类中的节点嵌入。其次，我们通过一种新颖的对相似性敏感的混合策略生成用于分类的困难节点类别，从而增强类间通用性。在流行的少样本节点分类数据集上进行的大量实验验证了我们框架的有效性，并证明了它相对于其他最先进的基准方法的优越性。
Few-shot node classification, which aims to predict labels for nodes on graphs with only limited labeled nodes as references, is of great significance in real-world graph mining tasks. To tackle such a label shortage issue, existing works generally leverage the meta-learning framework, which utilizes a number of episodes to extract transferable knowledge from classes with abundant labeled nodes and generalizes the knowledge to other classes with limited labeled nodes. In essence, the primary aim of few-shot node classification is to learn node embeddings that are generalizable across different classes. To accomplish this, the GNN encoder must be able to distinguish node embeddings between different classes, while also aligning embeddings for nodes in the same class. Thus, in this work, we propose to consider both the intra-class and inter-class generalizability of the model. We create a novel contrastive meta-learning framework on graphs, named COSMIC, with two key designs. First, we propose to enhance the intra-class generalizability by involving a contrastive two-step optimization in each episode to explicitly align node embeddings in the same classes. Second, we strengthen the inter-class generalizability by generating hard node classes for classification via a novel similarity-sensitive mix-up strategy. Extensive experiments on prevalent few-shot node classification datasets verify the effectiveness of our framework and demonstrate its superiority over other state-of-the-art baselines.