提出双层次混合方法，用更少任务实现高效图少样本学习
Dual-level Mixup for Graph Few-shot Learning with Fewer Tasks
- 设计任务内与任务间双重混合策略，扩充元学习中的节点和任务数据
- 在多个数据集上显著超越现有模型，跨域与同域设置均表现优异
- 适合资源有限、标注任务稀缺的图学习场景
图神经网络在网页结构化数据学习与内容挖掘中表现出强大能力。当前主流图模型需大量标注样本训练，导致少样本场景下易过拟合。尽管已有研究结合图学习与元学习缓解该问题，但多数模型依赖大量元训练任务以学习可迁移知识，而现实中构建任务成本高、难度大。为此，我们提出一种简单有效的少样本图学习方法SMILE。引入任务内与任务间双重混合策略，同时丰富元学习中的节点与任务多样性；此外，显式利用节点度信息编码更具表达力的节点表示。理论证明SMILE能提升模型泛化能力。实验表明，在所有评估数据集上，无论同域还是跨域设置，SMILE均显著优于其他竞争模型。
原文摘要 · Abstract (English)
Graph neural networks have been demonstrated as a powerful paradigm for effectively learning graph-structured data on the web and mining content from it.Current leading graph models require a large number of labeled samples for training, which unavoidably leads to overfitting in few-shot scenarios. Recent research has sought to alleviate this issue by simultaneously leveraging graph learning and meta-learning paradigms. However, these graph meta-learning models assume the availability of numerous meta-training tasks to learn transferable meta-knowledge. Such assumption may not be feasible in the real world due to the difficulty of constructing tasks and the substantial costs involved. Therefore, we propose a SiMple yet effectIve approach for graph few-shot Learning with fEwer tasks, named SMILE. We introduce a dual-level mixup strategy, encompassing both within-task and across-task mixup, to simultaneously enrich the available nodes and tasks in meta-learning. Moreover, we explicitly leverage the prior information provided by the node degrees in the graph to encode expressive node representations. Theoretically, we demonstrate that SMILE can enhance the model generalization ability. Empirically, SMILE consistently outperforms other competitive models by a large margin across all evaluated datasets with in-domain and cross-domain settings. Our anonymous code can be found here.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。