Method for multi-task learning fusion network traffic classification to address small sample labels

Author:

Liu Lan,Yu Yongjie,Wu Yafeng,Hui Zhanfa,Lin Jun,Hu Junhan

Abstract

AbstractIn the context of the proliferated evolution of network service types and the expeditious augmentation of network resource deployment, the requisition for copious labeled datasets to facilitate superior performance in traffic classification methods, particularly those hinging on deep learning, is imperative. Nonetheless, the procurement and annotation of such extensive datasets necessitate considerable temporal and human resource investments. In response to this predicament, this work introduces a methodology, termed MTEFU, leveraging a deep learning model-based multi-task learning algorithm, strategically designed to mitigate the reliance on substantial labeled training samples. Multiple classification tasks, encompassing duration, bandwidth size, and business traffic category, are incorporated, with a shared parameter strategy implemented amongst tasks to assure the transference of information across disparate tasks. Employing CNN, SAE, GRU, and LSTM as multi-task learning classification models, training validation and experimental testing were conducted on the QUIC dataset. A comparative analysis with single-task and ensemble learning methods reveals that, in the context of predicting network traffic types, the accuracy derived from the multi-task learning strategy, even with a mere 150 labeled samples, can emulate the 94.67% accuracy achieved through single-task learning with a fully labeled dataset of 6139 samples.

Funder

Education Department of Guangdong Province China

Publisher

Springer Science and Business Media LLC

Reference38 articles.

1. Ding, C., Chen, Y., Liu, Z., Alshehri, A. M. & Liu, T. Fractal characteristics of network traffic and its correlation with network security. Fractals 30(02), 2240067 (2022).

2. Mohammed, A. R., Mohammed, S. A. & Shirmohammadi, S. Machine learning and deep learning based traffic classification and prediction in software defined networking. In 2019 IEEE International Symposium on Measurements & Networking (M &N), 1–6 (IEEE, 2019).

3. Namdev, N., Agrawal, S. & Silkari, S. Recent advancement in machine learning based internet traffic classification. Proced. Comput. Sci. 60, 784–791 (2015).

4. Park, B., Won, Y. J., Choi, M. J., Kim, M. S. & Hong, J. W. Empirical analysis of application-level traffic classification using supervised machine learning. In Challenges for Next Generation Network Operations and Service Management, 11th Asia-Pacific Network Operations and Management Symposium, APNOMS 2008, Beijing, China, October 22-24, 2008. Proceedings (2008).

5. Kalaiselvi, T. & Shanmugaraja, P. Internet traffic classification using supervised learning algorithms-a survey. Int. Res. J. Eng. Technol. 3, 91–93 (2016).

Cited by 1 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Resource-Efficient Spectrum-Based Traffic Classification on Constrained Devices;IEEE Open Journal of the Communications Society;2024

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3