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 with (ii)
augmentations acting on time series sequence order and masking being a better
suit for TC and (iii) simple latent space analysis can provide hints about why
augmentations have positive or negative effects.

数据增强（DA）在计算机视觉（CV）和自然语言处理（NLP）领域被广泛采用以提高模型性能，然而在网络环境中，尤其是在流量分类（TC）任务中，数据增强一直存在问题。本文通过对 3 个 TC 数据集使用数据包时间序列作为输入表示，并考虑多种训练条件，基准测试了 18 种增强函数，结果显示（i）DA 可以获得以前未探索的优势，（ii）基于时间序列顺序和掩码的增强函数更适用于 TC，（iii）简单的潜在空间分析可以提供有关增强效果的线索。

交通分类的数据增强

Data Augmentation for Traffic Classification

The ability for a machine learning model to cope with differences in training
and deployment conditions--e.g. in the presence of distribution shift or the
generalization to new classes altogether--is crucial for real-world use cases.
However, most empirical work in this area has focused on the image domain with
artificial benchmarks constructed to measure individual aspects of
generalization. We present BIRB, a complex benchmark centered on the retrieval
of bird vocalizations from passively-recorded datasets given focal recordings
from a large citizen science corpus available for training. We propose a
baseline system for this collection of tasks using representation learning and
a nearest-centroid search. Our thorough empirical evaluation and analysis
surfaces open research directions, suggesting that BIRB fills the need for a
more realistic and complex benchmark to drive progress on robustness to
distribution shifts and generalization of ML models.

应对训练和部署条件的差异（例如分布偏移或对全新类别的泛化）对于机器学习模型在实际应用中至关重要。本研究提出了一个复杂的基准测试集 BIRB，以检索从大型公众科学语料库中经过被动记录的数据集中的鸟类声音。通过使用表示学习和最近质心搜索的基线系统，我们的实证评估和分析展示了开放性的研究方向，同时也建议 BIRB 作为更真实、更复杂的基准测试集，来推动对于分布偏移鲁棒性和机器学习模型泛化的进展。