AMBERT-DWPM: An Adaptive Masking and Dynamic Prototype Learning Framework for Few-Shot Text Classification
Journal Title: International Journal of Knowledge and Innovation Studies - Year 2025, Vol 3, Issue 1
Abstract
Transformer-based language models have demonstrated remarkable success in few-shot text classification; however, their effectiveness is often constrained by challenges such as high intraclass diversity and interclass similarity, which hinder the extraction of discriminative features. To address these limitations, a novel framework, Adaptive Masking Bidirectional Encoder Representations from Transformers with Dynamic Weighted Prototype Module (AMBERT-DWPM), is introduced, incorporating adaptive masking and dynamic weighted prototypical learning to enhance feature representation and classification performance. The standard BERT architecture is refined by integrating an adaptive masking mechanism based on Layered Integrated Gradients (LIG), enabling the model to dynamically emphasize salient text segments and improve feature discrimination. Additionally, a DWPM is designed to assign adaptive weights to support samples, mitigating inaccuracies in prototype construction caused by intraclass variability. Extensive evaluations conducted on six publicly available benchmark datasets demonstrate the superiority of AMBERT-DWPM over existing few-shot classification approaches. Notably, under the 5-shot setting on the DBpedia14 dataset, an accuracy of 0.978±0.004 is achieved, highlighting significant advancements in feature discrimination and generalization capabilities. These findings suggest that AMBERT-DWPM provides an efficient and robust solution for few-shot text classification, particularly in scenarios characterized by limited and complex textual data.
Authors and Affiliations
Junyu Li, Jialin Ma, Ashim Khadka
Keywords
Related Articles
- EP ID EP762893
- DOI https://doi.org/10.56578/ijkis030104
- Views 13
- Downloads 0
A Blockchain Cross-Chain Solution Based on Relays
Blockchain has attracted widespread attention due to its unique features such as decentralization, traceability, and tamper resistance. With the rapid development of blockchain technology, an increasing number of industr...
Enhanced Decision-Making with Advanced Algebraic Techniques in Complex Fermatean Fuzzy Sets under Confidence Levels
This study introduces novel algebraic techniques within the framework of complex Fermatean fuzzy sets (CFFSs) by incorporating confidence levels, presenting a suite of operators tailored for advanced decision-making. Spe...
Generalized and Group-Generalized Parameter Based Fermatean Fuzzy Aggregation Operators with Application to Decision-Making
Fermatean fuzzy set (FRFS) is very helpful in representing vague information that occurs in real world circumstances. Their eminent characteristic of FRFS is that the degree of membership ℑℓ and degree of non-membership...
Utilizing Edge Cloud Computing and Deep Learning for Enhanced Risk Assessment in China’s International Trade and Investment
Amidst a transformative economic milieu in China, domestic enterprises are venturing into the global market, exposing them to intensified perils in international trade and investment. This research elucidates the interna...
A Method for Creative Scheme Generation for Brand Design of Plush Toys Based on Extension Theory
In the era of branding, the design of plush toy brands often faces a contradiction with the needs of target user groups. Addressing the brand transformation challenges faced by small and micro enterprises in the plush to...