FewShotTextGCN: K-hop neighborhood regularization for few-shot learning on graphs

01/25/2023
by   Niels van der Heijden, et al.
0

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 ∼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 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.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset