MGIMN: Multi-Grained Interactive Matching Network for Few-shot Text Classification

TL;DR

This paper introduces MGIMN, a novel meta-learning approach for few-shot text classification that emphasizes instance-wise comparison and interaction, leading to improved performance over existing methods.

Contribution

MGIMN shifts from prototype-based to instance-wise comparison with interactive matching, capturing inter-dependencies for better few-shot text classification.

Findings

Significantly outperforms state-of-the-art methods in standard FSL.

Effective in generalized FSL settings.

Demonstrates the importance of instance-wise comparison and interaction.

Abstract

Text classification struggles to generalize to unseen classes with very few labeled text instances per class. In such a few-shot learning (FSL) setting, metric-based meta-learning approaches have shown promising results. Previous studies mainly aim to derive a prototype representation for each class. However, they neglect that it is challenging-yet-unnecessary to construct a compact representation which expresses the entire meaning for each class. They also ignore the importance to capture the inter-dependency between query and the support set for few-shot text classification. To deal with these issues, we propose a meta-learning based method MGIMN which performs instance-wise comparison followed by aggregation to generate class-wise matching vectors instead of prototype learning. The key of instance-wise comparison is the interactive matching within the class-specific context and episode-specific context. Extensive experiments demonstrate that the proposed method significantly outperforms the existing state-of-the-art approaches, under both the standard FSL and generalized FSL settings.