تقرير
FewShotTextGCN: K-hop neighborhood regularization for few-shot learning on graphs
| العنوان: | FewShotTextGCN: K-hop neighborhood regularization for few-shot learning on graphs |
|---|---|
| المؤلفون: | van der Heijden, Niels, Shutova, Ekaterina, Yannakoudakis, Helen |
| سنة النشر: | 2023 |
| المجموعة: | Computer Science |
| مصطلحات موضوعية: | Computer Science - Computation and Language, Computer Science - Machine Learning |
| الوصف: | 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. Comment: 8 pages, 4 figures, EACL 2023 |
| نوع الوثيقة: | Working Paper |
| الوصول الحر: | http://arxiv.org/abs/2301.10481Test |
| رقم الانضمام: | edsarx.2301.10481 |
| قاعدة البيانات: | arXiv |
| الوصف غير متاح. |