Aggregation and Pruning for Continuous Incremental Multi-Task Inference

Lining Li, Fenglin Cen, Quan Feng and Ji Xu ()
Additional contact information
Lining Li: College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China
Fenglin Cen: State Key Laboratory of Public Big Data, Guizhou University, Guiyang 550025, China
Quan Feng: Hunan Vanguard Group Corporation Limited, Changsha 410100, China
Ji Xu: State Key Laboratory of Public Big Data, Guizhou University, Guiyang 550025, China

Mathematics, 2025, vol. 13, issue 9, 1-18

Abstract: In resource-constrained mobile systems, efficiently handling incrementally added tasks under dynamically evolving requirements is a critical challenge. To address this, we propose aggregate pruning (AP), a framework that combines pruning with filter aggregation to optimize deep neural networks for continuous incremental multi-task learning (MTL). The approach reduces redundancy by dynamically pruning and aggregating similar filters across tasks, ensuring efficient use of computational resources while maintaining high task-specific performance. The aggregation strategy enables effective filter sharing across tasks, significantly reducing model complexity. Additionally, an adaptive mechanism is incorporated into AP to adjust filter sharing based on task similarity, further enhancing efficiency. Experiments on different backbone networks, including LeNet, VGG, ResNet, and so on, show that AP achieves substantial parameter reduction and computational savings with minimal accuracy loss, outperforming existing pruning methods and even surpassing non-pruning MTL techniques. The architecture-agnostic design of AP also enables potential extensions to complex architectures like graph neural networks (GNNs), offering a promising solution for incremental multi-task GNNs.

Keywords: pruning; multi-task learning; graph neural networks (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2025
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/13/9/1414/pdf (application/pdf)
https://www.mdpi.com/2227-7390/13/9/1414/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:13:y:2025:i:9:p:1414-:d:1642579

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().