TARU PUBLICATIONS
Journal of Information and Optimization Sciences cover

Journal of Information and Optimization Sciences

(Since 1980)
Hybrid ·Peer-reviewed·ISSN (Online): 2169-0103·ISSN (Print): 0252-2667

WoS  JIF 2026 : 0.4 (Q4)

Powered by:Powered by

Monthly Journal: Publishes theoretical and applied research on topics in information and optimization sciences.

Issues up to 2022 co-published with and available at:Taylor & Francis
submissions@tarupublications.com
Taru Online First Current IssueSpecial IssuesBrowse all Issues
Journal of Information and Optimization Sciences
Open Access Research Article

A framework for multi-task learning optimization in deep neural networks : Balancing task priorities for improved performance

* , , , , ,

* Corresponding author · click or hover a name for details

pp. 1141–1151Vol. 46Issue 4-BMay 2025DOI: 10.47974/JIOS-1898XML
Received:
16 Oct 2024
Published Online:
31 May 2025
Article type:
Research Article
Language:
EN
Article no.:
JIOS-1898
Pages:
1141–1151

Abstract

Deep neural networks (DNNs) have made multi-task learning (MTL) a powerful way to learn multiple linked tasks at once, using shared models to improve generalization and speed. But successfully matching task goals is still one of the biggest problems in MTL, since giving all tasks the same level of value often results in poor performance. To solve this problem, we suggest a new way to improve MTL in DNNs: job priorities should be balanced automatically based on how important they are. Our framework includes a task priority balance system that changes how much each job contributes to the total loss function as training goes on. This system uses measures that are relevant to the job, like how hard it is and how much data is available, to automatically assign resources and set learning priorities. By managing task priorities well, our system lets DNNs focus more on important tasks while giving the right amount of resources to less important ones, which makes all tasks run better overall. We show that our method works by doing a lot of tests on a bunch of different standard datasets from different fields. The results show that our system regularly does better than other MTL methods by being more accurate and more general, especially when job difficulties are uneven. Overall, our framework offers an adaptable and effective way to enhance MTL in DNNs, boosting performance by constantly balancing job priorities.

Keywords

Multi-task learning (MTL)Task prioritizationOptimizationFrameworkTask complexityResource allocationAdaptive learning

Subject Classifications

68T20

References

[1] J. Mills, J. Hu and G. Min, “Multi-Task Federated Learning for Personalised Deep Neural Networks in Edge Computing,” in IEEE Transactions on Parallel and Distributed Systems, vol. 33, no. 3, pp. 630-641, 1 March 2022
[2] N. V. Varghese and Q. H. Mahmoud, “A Hybrid Multi-Task Learning Approach for Optimizing Deep Reinforcement Learning Agents,” in IEEE Access, vol. 9, pp. 44681-44703 (2021).
[3] N. Ye, X. Li, H. Yu, L. Zhao, W. Liu and X. Hou, “DeepNOMA: A Unified Framework for NOMA Using Deep Multi-Task Learning,” in IEEE Transactions on Wireless Communications, vol. 19, no. 4, pp. 2208-2225, April (2020).
[4] N. V. Varghese and Q. H. Mahmoud, “Optimization of Deep Reinforcement Learning with Hybrid Multi-Task Learning,” 2021 IEEE International Systems Conference (SysCon), Vancouver, BC, Canada, pp. 1-8 (2021).
[5] N. V. Varghese and Q. H. Mahmoud, “Optimization of Deep Reinforcement Learning with Hybrid Multi-Task Learning,” 2021 IEEE International Systems Conference (SysCon), Vancouver, BC, Canada, pp. 1-8 (2021).
[6] T. Li, A. Sahu, A. Talwalkar and V. Smith, “Federated learning: Challenges methods and future directions”, IEEE Signal Process. Mag., vol. 37, no. 3, pp. 50-60, May (2020).
[7] A. G. Roy, S. Siddiqui, S. Pölsterl, N. Navab and C. Wachinger, “Braintorrent: A peer-to-peer environment for decentralized federated learning” (2019).
[8] C. T. Dinh, N. Tran and J. Nguyen, “Personalized federated learning with moreau envelopes”, Proc. Conf. Neural Inf. Process. Syst., vol. 33, pp. 21394-21405 (2020).
[9] A. Fallah, A. Mokhtari and A. Ozdaglar, “Personalized federated learning with theoretical guarantees: A model-agnostic meta-learning approach”, Proc. Conf. Neural Inf. Process. Syst., vol. 33, pp. 3557-3568 (2020).
[10] S. N. Ajani, P. Khobragade, M. Dhone, B. Ganguly, N. Shelke, and N. Parati, “Advancements in computing: Emerging trends in computational science with next-generation computing,” International Journal of Intelligent Systems and Applications in Engineering, vol. 12, no. 7s, pp. 546–559 (2023).
[11] H. He, S. Jin, C.-K. Wen, F. Gao, G. Y. Li and Z. Xu, “Model–driven deep learning for physical layer communications”, IEEE Wireless Commun., vol. 26, no. 5, pp. 77-83, Oct. (2019).
[12] A. Krishnan and E. Tanaka, “Adversarial Machine Learning: Attacks and Defenses in Deep Neural Networks”, Int Journal Adv Comp Theory Engg, vol. 12, no. 1, pp. 9–14, Apr. (2025). 
[13] S. Saika, S. Shewali, M. J. Borah, and D. J. Mahanta, “Arithmetic mean of interval valued intuitionistic fuzzy soft sets and its application in diagnosing infectious diseases,” J. Interdiscip. Math., vol. 27, no. 5, pp. 1079–1090 (2024), doi: 10.47974/JIM-1934.

Views: 199Downloads: 75Citations: 0