mlsanityData to 7 Oct 2026

Many or Few Samples? Comparing Transfer, Contrastive and Meta-Learning in Encrypted Traffic Classification

arXiv 2305.12432 ↗First posted 21 May 2023cs.LG cs.NIcited by 4

Not on the map. Why?

Abstract (arXiv)

The popularity of Deep Learning (DL), coupled with network traffic visibility reduction due to the increased adoption of HTTPS, QUIC and DNS-SEC, re-ignited interest towards Traffic Classification (TC). However, to tame the dependency from task-specific large labeled datasets we need to find better ways to learn representations that are valid across tasks. In this work we investigate this problem comparing transfer learning, meta-learning and contrastive learning against reference Machine Learning (ML) tree-based and monolithic DL models (16 methods total). Using two publicly available datasets, namely MIRAGE19 (40 classes) and AppClassNet (500 classes), we show that (i) using large datasets we can obtain more general representations, (ii) contrastive learning is the best methodology and (iii) meta-learning the worst one, and (iv) while ML tree-based cannot handle large tasks but fits well small tasks, by means of reusing learned representations, DL methods are reaching tree-based models performance also for small tasks.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 21 of its 49 references that are in the map. First posted on arXiv 21 May 2023.

Builds on

21 of 49 references.

References · 21

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  3. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  4. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  5. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  6. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  7. 2020Supervised Contrastive Learningcited by 2,803
  8. 2016Matching Networks for One Shot Learningcited by 2,246
  9. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
  10. 2017Revisiting Unreasonable Effectiveness of Data in Deep Learning Eracited by 916
  11. 2020Self-supervised Learning: Generative or Contrastivecited by 693
  12. 2019A Closer Look at Few-shot Classificationcited by 679
9 more
  1. 2019Generalizing from a Few Examples: A Survey on Few-Shot Learningcited by 462
  2. 2020Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?cited by 435
  3. 2018Meta-learning with differentiable closed-form solverscited by 395
  4. 2020Multi-Task Learning with Deep Neural Networks: A Surveycited by 374
  5. 2018How to Achieve High Classification Accuracy with Just a Few Labels: A Semi-supervised Approach Using Sampled Packetscited by 19
  6. 2021Deep Learning and Traffic Classification: Lessons learned from a commercial-grade dataset with hundreds of encrypted and zero-day applicationscited by 14
  7. 2022Fine-grained TLS services classification with reject optioncited by 14
  8. 2019Multitask Learning for Network Traffic Classificationcited by 11
  9. 2018A First Look at QUIC in the Wildcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 1; 2025: 1; 2026: 1.

4 papers.

  1. 2023Replication: Contrastive Learning and Data Augmentation in Traffic Classification Using a Flowpic Input Representationcited by 5
  2. 2024Data Augmentation for Traffic Classificationcited by 3
  3. 2025Universal Embedding Function for Traffic Classification via QUIC Domain Recognition Pretraining: A Transfer Learning Successcited by 1
  4. 2026SoK: Where Do Flow Labels Come From? Auditing Label Provenance in Encrypted Traffic Benchmarkscited by 1