Enhancing Deep Learning Semantics:The Diffusion Sampling and Label-Driven Co-Attention Approach

作     者：ChunhuaWang Wenqian Shang Tong Yi Haibin Zhu 

作者机构：State Key Laboratory of Media Convergence and CommunicationCommunication University of ChinaBeijing100024China School of Computer and Cyber SciencesCommunication University of ChinaBeijing100024China School of Computer Science and EngineeringGuangxi Normal UniversityGuilin541004China Department of Computer ScienceNipissing UniversityNorth BayON P1B 8L7Canada 

出 版 物：《Computers, Materials & Continua》 (计算机、材料和连续体（英文）)

年 卷 期：2024年第79卷第5期

页      面：1939-1956页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 08[工学] 0805[工学-材料科学与工程（可授工学、理学学位）] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：the Communication University of China(CUC230A013) the Fundamental Research Funds for the Central Universities 

主　　题：Semantic representation sampling attention label-driven co-attention attention mechanisms 

摘      要：The advent of self-attention mechanisms within Transformer models has significantly propelled the advancement of deep learning algorithms,yielding outstanding achievements across diverse ***,self-attention mechanisms falter when applied to datasets with intricate semantic content and extensive dependency *** response,this paper introduces a Diffusion Sampling and Label-Driven Co-attention Neural Network(DSLD),which adopts a diffusion sampling method to capture more comprehensive semantic information of the ***,themodel leverages the joint correlation information of labels and data to introduce the computation of text representation,correcting semantic representationbiases in thedata,andincreasing the accuracyof semantic ***,the model computes the corresponding classification results by synthesizing these rich data semantic *** on seven benchmark datasets show that our proposed model achieves competitive results compared to state-of-the-art methods.