# How to Achieve High Classification Accuracy with Just a Few Labels: A Semi-supervised Approach Using Sampled Packets

arXiv: https://arxiv.org/abs/1812.09761 · HTML: https://mlsanity.com/paper/1812.09761/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Dec 2018.

## Built on by (most cited first, 19 of 19)

- [Fine-grained TLS services classification with reject option](https://mlsanity.com/paper/2202.11984/) (2022)
- [Extensible Machine Learning for Encrypted Network Traffic Application Labeling via Uncertainty Quantification](https://mlsanity.com/paper/2205.05628/) (2022)
- [Active Learning for Network Traffic Classification: A Technical Study](https://mlsanity.com/paper/2106.06933/) (2021)
- [When a RF Beats a CNN and GRU, Together -- A Comparison of Deep Learning and Classical Machine Learning Approaches for Encrypted Malware Traffic Classification](https://mlsanity.com/paper/2206.08004/) (2022)
- [Replication: Contrastive Learning and Data Augmentation in Traffic Classification Using a Flowpic Input Representation](https://mlsanity.com/paper/2309.09733/) (2023)
- [Many or Few Samples? Comparing Transfer, Contrastive and Meta-Learning in Encrypted Traffic Classification](https://mlsanity.com/paper/2305.12432/) (2023)
- [When Simple Model Just Works: Is Network Traffic Classification in Crisis?](https://mlsanity.com/paper/2506.08655/) (2025)
- [Data Augmentation for Traffic Classification](https://mlsanity.com/paper/2401.10754/) (2024)
- [AutoML4ETC: Automated Neural Architecture Search for Real-World Encrypted Traffic Classification](https://mlsanity.com/paper/2308.02182/) (2023)
- [Modeling Live Video Streaming: Real-Time Classification, QoE Inference, and Field Evaluation](https://mlsanity.com/paper/2112.02637/) (2021)
- [Open-Source Framework for Encrypted Internet and Malicious Traffic Classification](https://mlsanity.com/paper/2206.10144/) (2022)
- [Generic Multi-modal Representation Learning for Network Traffic Analysis](https://mlsanity.com/paper/2405.02649/) (2024)
- [Non-uniformity is All You Need: Efficient and Timely Encrypted Traffic Classification With ECHO](https://mlsanity.com/paper/2406.01852/) (2024)
- [Universal Embedding Function for Traffic Classification via QUIC Domain Recognition Pretraining: A Transfer Learning Success](https://mlsanity.com/paper/2502.12930/) (2025)
- [FedEdge AI-TC: A Semi-supervised Traffic Classification Method based on Trusted Federated Deep Learning for Mobile Edge Computing](https://mlsanity.com/paper/2308.06924/) (2023)
- [CBR -- Boosting Adaptive Classification By Retrieval of Encrypted Network Traffic with Out-of-distribution](https://mlsanity.com/paper/2403.11206/) (2024)
- [FedAuxHMTL: Federated Auxiliary Hard-Parameter Sharing Multi-Task Learning for Network Edge Traffic Classification](https://mlsanity.com/paper/2404.08028/) (2024)
- [Enhancing Encrypted Internet Traffic Classification Through Advanced Data Augmentation Techniques](https://mlsanity.com/paper/2407.16539/) (2024)
- [Learning QoE from Packet-Level Measurements in Encrypted Video Conferencing Traffic](https://mlsanity.com/paper/2601.06862/) (2026)

## Abstract (arXiv)

Network traffic classification, which has numerous applications from security to billing and network provisioning, has become a cornerstone of today's computer networks. Previous studies have developed traffic classification techniques using classical machine learning algorithms and deep learning methods when large quantities of labeled data are available. However, capturing large labeled datasets is a cumbersome and time-consuming process. In this paper, we propose a semi-supervised approach that obviates the need for large labeled datasets. We first pre-train a model on a large unlabeled dataset where the input is the time series features of a few sampled packets. Then the learned weights are transferred to a new model that is re-trained on a small labeled dataset. We show that our semi-supervised approach achieves almost the same accuracy as a fully-supervised method with a large labeled dataset, though we use only 20 samples per class. In tests based on a dataset generated from the more challenging QUIC protocol, our approach yields 98% accuracy. To show its efficacy, we also test our approach on two public datasets. Moreover, we study three different sampling techniques and demonstrate that sampling packets from an arbitrary portion of a flow is sufficient for classification.