论文标题
使用特定于任务的结构进行少量学习学习
Graph Few-shot Learning with Task-specific Structures
论文作者
论文摘要
在各种图形学习任务中，几乎没有图形学习至关重要。在几次射击情况下，通常需要模型进行分类，但给定标记的样品有限。现有的图形少数学习方法通常利用图形神经网络（GNN）并在一系列元任务中执行分类。然而，这些方法通常依赖于原始图（即，从中取样元任务的图）来学习节点表示。因此，每个元任务中使用的图形结构是相同的。由于类别的类别在元任务中不同，因此应以特定于任务的方式学习节点表示形式，以促进分类性能。因此，为了自适应地学习跨任务的节点表示形式，我们提出了一个新颖的框架，该框架可以学习每个元任务的特定任务结构。为了处理跨任务中各种节点的多样性，我们提取相关节点并根据节点影响和相互信息学习特定于任务的结构。这样，我们可以通过为每个元任务量身定制的任务特定结构来学习节点表示。我们进一步对单颗和多射线设置下的五个节点分类数据集进行了广泛的实验，以验证我们的框架优越性优于最先进的基线。我们的代码可在https://github.com/songw-sw/glitter上提供。
Graph few-shot learning is of great importance among various graph learning tasks. Under the few-shot scenario, models are often required to conduct classification given limited labeled samples. Existing graph few-shot learning methods typically leverage Graph Neural Networks (GNNs) and perform classification across a series of meta-tasks. Nevertheless, these methods generally rely on the original graph (i.e., the graph that the meta-task is sampled from) to learn node representations. Consequently, the graph structure used in each meta-task is identical. Since the class sets are different across meta-tasks, node representations should be learned in a task-specific manner to promote classification performance. Therefore, to adaptively learn node representations across meta-tasks, we propose a novel framework that learns a task-specific structure for each meta-task. To handle the variety of nodes across meta-tasks, we extract relevant nodes and learn task-specific structures based on node influence and mutual information. In this way, we can learn node representations with the task-specific structure tailored for each meta-task. We further conduct extensive experiments on five node classification datasets under both single- and multiple-graph settings to validate the superiority of our framework over the state-of-the-art baselines. Our code is provided at https://github.com/SongW-SW/GLITTER.
