AttenFlow: Context-Aware Architecture with Consensus-Based Retrieval and Graph Attention for Automated Document Processing
Automated document processing and circulation systems face critical challenges in achieving reliable retrieval accuracy and robust classification performance, particularly in security-critical organizational environments. Traditional approaches suffer from fundamental limitations, including fixed fu...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-07-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/13/7517 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849319828725170176 |
|---|---|
| author | Xianfeng Zhang Bin Hu Shukan Liu Qiao Sun Lin Chen |
| author_facet | Xianfeng Zhang Bin Hu Shukan Liu Qiao Sun Lin Chen |
| author_sort | Xianfeng Zhang |
| collection | DOAJ |
| description | Automated document processing and circulation systems face critical challenges in achieving reliable retrieval accuracy and robust classification performance, particularly in security-critical organizational environments. Traditional approaches suffer from fundamental limitations, including fixed fusion strategies in hybrid retrieval systems, inability to model inter-document relationships in classification tasks, and lack of confidence estimation for result reliability. This paper introduces AttenFlow, a novel context-aware architecture that revolutionizes document management through two core technical innovations. First, we propose the retriever consensus confidence fusion (RCCF) method, which addresses the limitations of conventional hybrid retrieval approaches by introducing consensus-based fusion strategies that dynamically adapt to retriever agreement levels while providing confidence estimates for results. RCCF measures the consensus between different retrievers through sophisticated ranking and scoring consistency metrics, enabling adaptive weight assignment that amplifies high-consensus results while adopting conservative approaches for uncertain cases. Second, we develop adversarial mutual-attention hybrid-dimensional graph attention network (AM-HDGAT) for text, which transforms document classification by modeling inter-document relationships through graph structures while integrating high-dimensional semantic features and low-dimensional statistical features through mutual-attention mechanisms. The approach incorporates adversarial training to enhance robustness against potential security threats, making it particularly suitable for critical document processing applications. Comprehensive experimental evaluation across multiple benchmark datasets demonstrates the substantial effectiveness of our innovations. RCCF achieves improvements of up to 16.9% in retrieval performance metrics compared to traditional fusion methods while providing reliable confidence estimates. AM-HDGAT for text demonstrates superior classification performance with an average F1-score improvement of 2.23% compared to state-of-the-art methods, maintaining 82.4% performance retention under adversarial attack scenarios. Real-world deployment validation shows a 34.5% reduction in manual processing time and 95.7% user satisfaction scores, establishing AttenFlow as a significant advancement in intelligent document management technology. |
| format | Article |
| id | doaj-art-1c16a6744be04dbbbe8f7d844735fdea |
| institution | Kabale University |
| issn | 2076-3417 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-1c16a6744be04dbbbe8f7d844735fdea2025-08-20T03:50:17ZengMDPI AGApplied Sciences2076-34172025-07-011513751710.3390/app15137517AttenFlow: Context-Aware Architecture with Consensus-Based Retrieval and Graph Attention for Automated Document ProcessingXianfeng Zhang0Bin Hu1Shukan Liu2Qiao Sun3Lin Chen4School of Electronic Engineering, Naval University of Engineering, Wuhan 430068, ChinaSchool of Electronic Engineering, Naval University of Engineering, Wuhan 430068, ChinaSchool of Electronic Engineering, Naval University of Engineering, Wuhan 430068, ChinaSchool of Electronic Engineering, Naval University of Engineering, Wuhan 430068, ChinaSchool of Electronic Engineering, Naval University of Engineering, Wuhan 430068, ChinaAutomated document processing and circulation systems face critical challenges in achieving reliable retrieval accuracy and robust classification performance, particularly in security-critical organizational environments. Traditional approaches suffer from fundamental limitations, including fixed fusion strategies in hybrid retrieval systems, inability to model inter-document relationships in classification tasks, and lack of confidence estimation for result reliability. This paper introduces AttenFlow, a novel context-aware architecture that revolutionizes document management through two core technical innovations. First, we propose the retriever consensus confidence fusion (RCCF) method, which addresses the limitations of conventional hybrid retrieval approaches by introducing consensus-based fusion strategies that dynamically adapt to retriever agreement levels while providing confidence estimates for results. RCCF measures the consensus between different retrievers through sophisticated ranking and scoring consistency metrics, enabling adaptive weight assignment that amplifies high-consensus results while adopting conservative approaches for uncertain cases. Second, we develop adversarial mutual-attention hybrid-dimensional graph attention network (AM-HDGAT) for text, which transforms document classification by modeling inter-document relationships through graph structures while integrating high-dimensional semantic features and low-dimensional statistical features through mutual-attention mechanisms. The approach incorporates adversarial training to enhance robustness against potential security threats, making it particularly suitable for critical document processing applications. Comprehensive experimental evaluation across multiple benchmark datasets demonstrates the substantial effectiveness of our innovations. RCCF achieves improvements of up to 16.9% in retrieval performance metrics compared to traditional fusion methods while providing reliable confidence estimates. AM-HDGAT for text demonstrates superior classification performance with an average F1-score improvement of 2.23% compared to state-of-the-art methods, maintaining 82.4% performance retention under adversarial attack scenarios. Real-world deployment validation shows a 34.5% reduction in manual processing time and 95.7% user satisfaction scores, establishing AttenFlow as a significant advancement in intelligent document management technology.https://www.mdpi.com/2076-3417/15/13/7517document processingconsensus-based retrieval fusiongraph attention networksadversarial trainingcontext-aware architecture |
| spellingShingle | Xianfeng Zhang Bin Hu Shukan Liu Qiao Sun Lin Chen AttenFlow: Context-Aware Architecture with Consensus-Based Retrieval and Graph Attention for Automated Document Processing Applied Sciences document processing consensus-based retrieval fusion graph attention networks adversarial training context-aware architecture |
| title | AttenFlow: Context-Aware Architecture with Consensus-Based Retrieval and Graph Attention for Automated Document Processing |
| title_full | AttenFlow: Context-Aware Architecture with Consensus-Based Retrieval and Graph Attention for Automated Document Processing |
| title_fullStr | AttenFlow: Context-Aware Architecture with Consensus-Based Retrieval and Graph Attention for Automated Document Processing |
| title_full_unstemmed | AttenFlow: Context-Aware Architecture with Consensus-Based Retrieval and Graph Attention for Automated Document Processing |
| title_short | AttenFlow: Context-Aware Architecture with Consensus-Based Retrieval and Graph Attention for Automated Document Processing |
| title_sort | attenflow context aware architecture with consensus based retrieval and graph attention for automated document processing |
| topic | document processing consensus-based retrieval fusion graph attention networks adversarial training context-aware architecture |
| url | https://www.mdpi.com/2076-3417/15/13/7517 |
| work_keys_str_mv | AT xianfengzhang attenflowcontextawarearchitecturewithconsensusbasedretrievalandgraphattentionforautomateddocumentprocessing AT binhu attenflowcontextawarearchitecturewithconsensusbasedretrievalandgraphattentionforautomateddocumentprocessing AT shukanliu attenflowcontextawarearchitecturewithconsensusbasedretrievalandgraphattentionforautomateddocumentprocessing AT qiaosun attenflowcontextawarearchitecturewithconsensusbasedretrievalandgraphattentionforautomateddocumentprocessing AT linchen attenflowcontextawarearchitecturewithconsensusbasedretrievalandgraphattentionforautomateddocumentprocessing |