鉴别器
计算机科学
人工智能
对抗制
元学习(计算机科学)
机器学习
领域(数学分析)
杠杆(统计)
对偶(语法数字)
一般化
发电机(电路理论)
模式识别(心理学)
任务(项目管理)
数学
功率(物理)
艺术
电信
数学分析
管理
文学类
量子力学
经济
物理
探测器
作者
Xuyang Wang,Yajun Du,Danroujing Chen,Xianyong Li,Xiaoliang Chen,Yongquan Fan,Chunzhi Xie,Yanli Li,Jia Liu,Hui Li
标识
DOI:10.1016/j.asoc.2023.110697
摘要
Meta-learning-based methods prevail in few-shot text classification. Current methods perform meta-training and meta-testing on two parts of a dataset in the same or similar domains. This results in a significant limit in model performance when faced with data from different domains, limiting the generalization of few-shot models. To solve this problem, this study proposes a new setting, namely, domain-generalized few-shot text classification. First, meta-training is conducted on a multi-domain dataset to learn a generalizable model. Subsequently, the model is meta-tested on a target dataset. In addition, a domain-generalized model, namely, a dual adversarial network, is designed to improve the meta-learning-based methods under domain drift between different datasets and domains. Unlike previous meta-learning methods, two N-way-K-shot tasks were input from different domains for a dual adversarial network at each episode. Dual adversarial networks leverage the features from two different domains for adversarial training to improve the domain adaptability of the model. The proposed model utilizes a domain-knowledge generator during adversarial training to produce domain-specific knowledge, and a domain discriminator to recognize the domain label of the produced knowledge. Extensive experiments are conducted to verify the effectiveness of the proposed settings and model. The experimental results show that the model performance in our proposed setting is improved by an average of 3.84% compared to that in cross-domain few-shot text classification. Furthermore, the dual adversarial network significantly outperforms the five competitive baseline models, with an average improvement of 7.20%. The proposed model achieves an average performance improvement of 2.69% compared with the best baseline method.
科研通智能强力驱动
Strongly Powered by AbleSci AI