Handling partially labeled network data: A semi-supervised approach using stacked sparse autoencoder

Aouedi, Ons; Piamrat, Kandaraj; Bagadthey, Dhruvjyoti

doi:10.1016/j.comnet.2021.108742

Cited by 7 publications

(2 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this respect, there are two main reasons why we believe that RL is a good candidate for the controller synchronization problem. The first reason is that, in wireless networks where several applications with human involvement exist, it is almost impossible to find labelled data for training the ML algorithms, whereas unlabelled data are often abundant and easily available [62]. Secondly, optimizing the synchronization process for heterogeneous networks is indeed a long-term decision that is affected by multiple conditions.…”

Section: Proposed Solutionmentioning

confidence: 99%

Integration of Network Slicing and Machine Learning into Edge Networks for Low-Latency Services in 5G and beyond Systems

2022

View full text Add to dashboard Cite

Fifth-generation (5G) and beyond networks are envisioned to serve multiple emerging applications having diverse and strict quality of service (QoS) requirements. To meet ultra-reliable and low latency communication, real-time data processing and massive device connectivity demands of the new services, network slicing and edge computing, are envisioned as key enabling technologies. Network slicing will prioritize virtualized and dedicated logical networks over common physical infrastructure and encourage flexible and scalable networks. On the other hand, edge computing offers storage and computational resources at the edge of networks, hence providing real-time, high-bandwidth, low-latency access to radio network resources. As the integration of two technologies delivers network capabilities more efficiently and effectively, this paper provides a comprehensive study on edge-enabled network slicing frameworks and potential solutions with example use cases. In addition, this article further elaborated on the application of machine learning in edge-sliced networks and discussed some recent works as well as example deployment scenarios. Furthermore, to reveal the benefits of these systems further, a novel framework based on reinforcement learning for controller synchronization in distributed edge sliced networks is proposed.

show abstract

Section: Proposed Solutionmentioning

confidence: 99%

Integration of Network Slicing and Machine Learning into Edge Networks for Low-Latency Services in 5G and beyond Systems

2022

View full text Add to dashboard Cite

show abstract

“…To tackle this problem, some studies in recent years have combined the SAE with semi-supervised learning. For the classification of partially labeled network traffic samples, Aouedi et al [ 23 ] proposed the semi-supervised stacked autoencoder (Semi-SAE) to realize a semi-supervised learning of the SAE. This method needs unsupervised feature extraction for all samples in the pre-training stage and fine-tuning of the network parameters based on the classification loss of the labeled samples.…”

Section: Introductionmentioning

confidence: 99%

A Semi-Supervised Stacked Autoencoder Using the Pseudo Label for Classification Tasks

Lai,

Wang,

Xiang

et al. 2023

Entropy

View full text Add to dashboard Cite

The efficiency and cognitive limitations of manual sample labeling result in a large number of unlabeled training samples in practical applications. Making full use of both labeled and unlabeled samples is the key to solving the semi-supervised problem. However, as a supervised algorithm, the stacked autoencoder (SAE) only considers labeled samples and is difficult to apply to semi-supervised problems. Thus, by introducing the pseudo-labeling method into the SAE, a novel pseudo label-based semi-supervised stacked autoencoder (PL-SSAE) is proposed to address the semi-supervised classification tasks. The PL-SSAE first utilizes the unsupervised pre-training on all samples by the autoencoder (AE) to initialize the network parameters. Then, by the iterative fine-tuning of the network parameters based on the labeled samples, the unlabeled samples are identified, and their pseudo labels are generated. Finally, the pseudo-labeled samples are used to construct the regularization term and fine-tune the network parameters to complete the training of the PL-SSAE. Different from the traditional SAE, the PL-SSAE requires all samples in pre-training and the unlabeled samples with pseudo labels in fine-tuning to fully exploit the feature and category information of the unlabeled samples. Empirical evaluations on various benchmark datasets show that the semi-supervised performance of the PL-SSAE is more competitive than that of the SAE, sparse stacked autoencoder (SSAE), semi-supervised stacked autoencoder (Semi-SAE) and semi-supervised stacked autoencoder (Semi-SSAE).

show abstract

Network traffic classification based‐ masked language regression model using CNN

P. L.,

Emmanuel,

Rani

2024

Concurrency and Computation

View full text Add to dashboard Cite

SummaryNetwork traffic classification task has become increasingly challenging. The objective behind this classification is to effectively handle bandwidth, prioritize certain types of traffic, enhance application performance, and more. In recent times, there has been a surge in exploring deep learning approaches for network traffic categorization. However, these models demand substantial volumes of training data. Additionally, many classification methods necessitate manual feature extraction, a process that is not only time‐consuming but also laborious. Addressing the challenge of identifying optimal features to enhance classification accuracy, this work introduces a deep learning model designed for effective classification of network traffic. The model comprises the following key stages: (a) The dataset involves TCP flows captured from running different network stress and web crawling tools, (b) Pre‐processing for removal of anomalies and noises using Label Encoder and OneHotEncoder, (c) The utilization of K‐BERT for feature extraction aims to retrieve local spatial–temporal features, (d) feature selection using linear regression model (LASSO) and finally, and (e) The classification of network traffic involves neural network. The model serves to enhance the precision and efficiency of the classification mission. Through comprehensive experimental analysis, it was observed that the Masked Language‐based Regression model surpassed other referenced models, achieving an exceptional accuracy of 0.97.

show abstract

Handling partially labeled network data: A semi-supervised approach using stacked sparse autoencoder

Cited by 7 publications

References 33 publications

Integration of Network Slicing and Machine Learning into Edge Networks for Low-Latency Services in 5G and beyond Systems

Integration of Network Slicing and Machine Learning into Edge Networks for Low-Latency Services in 5G and beyond Systems

A Semi-Supervised Stacked Autoencoder Using the Pseudo Label for Classification Tasks

Network traffic classification based‐ masked language regression model using CNN

Contact Info

Product

Resources

About