文献类型：期刊文献

英文题名：IPCL: Cross-Domain Invariant Prototypical Contrastive Learning for Few-Shot Text Classification

作者：Mao, Shucheng[1];Cheng, Hua[1];Cheng, Tao[1];Fang, Yiquan[1];Yang, Mingyu[1];Chen, Xiaoning[1]

机构：[1]East China Univ Sci & Technol, Sch Informat Sci & Engn, 130 Meilong Rd, Shanghai 200237, Peoples R China

年份：2026

外文期刊名：INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE

收录：;EI(收录号：20262020734867);WOS:【SCI-EXPANDED(收录号:WOS:001762186100001)】；

语种：英文

外文关键词：Few-shot learning; prototypical contrastive learning; domain adaption

摘要：Prototypical networks are a typical method in few-shot learning. The instance-based training causes the model to learn specific domain features of the support set, leading to inadequate cross-domain generalization capabilities when faced with new domain data. To this end, this paper proposes a cross-domain Invariant Prototypical Contrastive Learning (IPCL) method. We extract invariant features (content features) and abstract invariant features (emotional features) from sample characteristics to construct invariant prototypes, which are domain-independent. Based on invariant representation learning, the model decouples latent features to obtain invariant features, which form the core basis for classification decisions. Abstract invariant features, refined from variable features (style features), reveal the underlying commonalities behind these variable features. Furthermore, we propose constructing auxiliary classification tasks that directly mine invariant prototype's semantic features, combined with metric tasks to achieve cross-task information complementarity and enhance the model's generalization ability to new domains. Experiments show that IPCL's decoupling of latent variables is recognizable, achieving accuracies of 92.23% and 93.45% on the ARSC and SST-2 datasets, respectively. In cross-domain tasks, IPCL outperforms previous method by up to 1.11%, demonstrating IPCL's superior cross-domain generalization capabilities.