PAM 2024, Passive and Active Measurement Conference, 11-13 March 2024 (Virtual Event)
Runner-up Best Paper Award
Data Augmentation (DA)—enriching training data by adding synthetic samples—is a technique widely adopted in Computer Vision (CV) and Natural Language Processing (NLP) tasks to improve models performance. Yet, DA has struggled to gain traction in networking contexts, particularly in Traffic Classification (TC) tasks. In this work,
we fulfill this gap by benchmarking 18 augmentation functions applied to 3 TC datasets using packet time series as input representation and considering a variety of training conditions. Our results show that (i) DA can reap benefits previously unexplored, (ii) augmentations acting on time series sequence order and masking are better suited for TC than amplitude augmentations and (iii) basic models latent space analysis can help understanding the positive/negative effects of augmentations on classification performance.
Type:
Conference
Date:
2024-03-11
Department:
Data Science
Eurecom Ref:
7584
Copyright:
© Springer. Personal use of this material is permitted. The definitive version of this paper was published in PAM 2024, Passive and Active Measurement Conference, 11-13 March 2024 (Virtual Event) and is available at : https://doi.org/10.1007/978-3-031-56249-5_7
See also: