Dynamic Memory Induction Networks for Few-Shot Text Classification

TL;DR

This paper introduces Dynamic Memory Induction Networks (DMIN) that leverage dynamic routing and query information to improve few-shot text classification, achieving state-of-the-art results on benchmark datasets.

Contribution

The paper presents a novel DMIN model that enhances memory-based few-shot learning with dynamic routing and query-aware induction, improving adaptability and generalization.

Findings

Achieves 2-4% higher accuracy on miniRCV1 and ODIC datasets.

Demonstrates the effectiveness of dynamic routing in few-shot learning.

Provides detailed analysis validating each component's contribution.

Abstract

This paper proposes Dynamic Memory Induction Networks (DMIN) for few-shot text classification. The model utilizes dynamic routing to provide more flexibility to memory-based few-shot learning in order to better adapt the support sets, which is a critical capacity of few-shot classification models. Based on that, we further develop induction models with query information, aiming to enhance the generalization ability of meta-learning. The proposed model achieves new state-of-the-art results on the miniRCV1 and ODIC dataset, improving the best performance (accuracy) by 2~4%. Detailed analysis is further performed to show the effectiveness of each component.