论文标题
跨域少数图形分类
Cross-Domain Few-Shot Graph Classification
论文作者
论文摘要
我们通过引入三个由公开可用数据集构建的新的跨域基准测试，研究了跨域中几乎没有射击图分类的问题。我们还提出了一个基于注意力的图形编码器，该编码器使用三个一致的图表观点，一个上下文和两个拓扑视图，以了解特定于任务信息的表示，以进行快速适应，以及用于知识传输的任务信息信息。我们进行详尽的实验，以评估对比度和元学习策略的性能。我们表明，与基于公制的元学习框架相结合时，所提出的编码器可在所有基准测试中实现最佳的平均元检验分类精度。源代码和数据将在此处发布：https：//github.com/kavehhassani/metagrl
We study the problem of few-shot graph classification across domains with nonequivalent feature spaces by introducing three new cross-domain benchmarks constructed from publicly available datasets. We also propose an attention-based graph encoder that uses three congruent views of graphs, one contextual and two topological views, to learn representations of task-specific information for fast adaptation, and task-agnostic information for knowledge transfer. We run exhaustive experiments to evaluate the performance of contrastive and meta-learning strategies. We show that when coupled with metric-based meta-learning frameworks, the proposed encoder achieves the best average meta-test classification accuracy across all benchmarks. The source code and data will be released here: https://github.com/kavehhassani/metagrl
