论文标题
基于图谱测量的超级级别上的图形学习很少
Few-Shot Learning on Graphs via Super-Classes based on Graph Spectral Measures
论文作者
论文摘要
我们建议研究图形神经网络（GNN）中很少的镜头图分类的问题，以识别未见类的类别，给定标记的图形示例有限。尽管最近提出了一些有关节点和图形分类任务的有趣的GNN变体，但面对少数射击设置的示例稀缺，这些GNN在分类性能方面表现出重大损失。在这里，我们提出了一种方法，其中根据图归一化的laplacian将概率度量分配给每个图。这使我们能够相应地将与每个图相关联的图基标签聚集到超级类中，其中LP Wasserstein距离用作我们的基础距离度量。随后，将基于超级类构建的超级图被馈送到我们提出的GNN框架中，该框架利用超级图与Super Graph显式建立的潜在类别间关系，以实现图形之间更好的类标签分离。我们对我们提出的方法进行详尽的经验评估，并表明它的表现既优于少数射击场景的最先进的图形分类方法的适应性，又超过了我们的天真基线GNN。此外，我们还将方法的行为扩展到半监督和主动学习方案。
We propose to study the problem of few shot graph classification in graph neural networks (GNNs) to recognize unseen classes, given limited labeled graph examples. Despite several interesting GNN variants being proposed recently for node and graph classification tasks, when faced with scarce labeled examples in the few shot setting, these GNNs exhibit significant loss in classification performance. Here, we present an approach where a probability measure is assigned to each graph based on the spectrum of the graphs normalized Laplacian. This enables us to accordingly cluster the graph base labels associated with each graph into super classes, where the Lp Wasserstein distance serves as our underlying distance metric. Subsequently, a super graph constructed based on the super classes is then fed to our proposed GNN framework which exploits the latent inter class relationships made explicit by the super graph to achieve better class label separation among the graphs. We conduct exhaustive empirical evaluations of our proposed method and show that it outperforms both the adaptation of state of the art graph classification methods to few shot scenario and our naive baseline GNNs. Additionally, we also extend and study the behavior of our method to semi supervised and active learning scenarios.
