Boosting Meta-Learning for Few-Shot Text Classification via Label-guided Distance Scaling

TL;DR

This paper introduces a label-guided distance scaling strategy that leverages label semantics to improve few-shot text classification, addressing the challenge of ineffective supervision during testing.

Contribution

It proposes a novel label-guided loss and scaler that utilize label semantics in both training and testing to enhance meta-learning for few-shot text classification.

Findings

Significantly outperforms state-of-the-art models on multiple datasets.

Effectively mitigates misclassification caused by distant sample representations.

Demonstrates robustness across different meta-learning frameworks.

Abstract

Few-shot text classification aims to recognize unseen classes with limited labeled text samples. Existing approaches focus on boosting meta-learners by developing complex algorithms in the training stage. However, the labeled samples are randomly selected during the testing stage, so they may not provide effective supervision signals, leading to misclassification. To address this issue, we propose a \textbf{L}abel-guided \textbf{D}istance \textbf{S}caling (LDS) strategy. The core of our method is exploiting label semantics as supervision signals in both the training and testing stages. Specifically, in the training stage, we design a label-guided loss to inject label semantic information, pulling closer the sample representations and corresponding label representations. In the testing stage, we propose a Label-guided Scaler which scales sample representations with label semantics to provide additional supervision signals. Thus, even if labeled sample representations are far from class centers, our Label-guided Scaler pulls them closer to their class centers, thereby mitigating the misclassification. We combine two common meta-learners to verify the effectiveness of the method. Extensive experimental results demonstrate that our approach significantly outperforms state-of-the-art models. All datasets and codes are available at https://anonymous.4open.science/r/Label-guided-Text-Classification.