We present FewShotTextGCN, a novel method designed to effectively utilize the properties of word-document graphs for improved learning in low-resource settings. We introduce K-hop Neighbourhood Regularization, a regularizer for heterogeneous graphs, and show that it stabilizes and improves learning when only a few training samples are available. We furthermore propose a simplification in the graph-construction method, which results in a graph that is $\sim$7 times less dense and yields better performance in little-resource settings while performing on par with the state of the art in high-resource settings. Finally, we introduce a new variant of Adaptive Pseudo-Labeling tailored for word-document graphs. When using as little as 20 samples for training, we outperform a strong TextGCN baseline with 17% in absolute accuracy on average over eight languages. We demonstrate that our method can be applied to document classification without any language model pretraining on a wide range of typologically diverse languages while performing on par with large pretrained language models.

翻译：我们提出FewShotTextGCN方法，旨在有效利用词-文档图属性以改进低资源场景下的学习性能。引入面向异质图的K跳邻域正则化器，证明其在仅有少量训练样本时可稳定并提升学习效果。进一步简化图构建方法，使图密度降低约7倍，在低资源场景下取得更优性能，而在高资源场景下性能与现有最优方法持平。最后，提出针对词-文档图的自适应伪标签新变体。当仅使用20个训练样本时，我们在八种语言上的平均绝对准确率超越强基线TextGCN模型达17%。实验证明，该方法无需任何语言模型预训练即可应用于跨类型学语言的文档分类任务，且性能与大规模预训练语言模型相媲美。