Group & Reweight: A Novel Cost-Sensitive Approach to Mitigating Class Imbalance in Network Traffic Classification
This addresses class imbalance for network traffic classification, particularly for numerous minority malicious classes, with an incremental method building on group distributionally optimization.
The paper tackles severe class imbalance in network traffic classification, which skews decision boundaries and raises safety concerns, by proposing a group & reweight strategy that clusters classes and optimizes reweighted losses, achieving improved comprehensive performance in prediction.
Internet services have led to the eruption of network traffic, and machine learning on these Internet data has become an indispensable tool, especially when the application is risk-sensitive. This paper focuses on network traffic classification in the presence of severe class imbalance. Such a distributional trait mostly drifts the optimal decision boundary and results in an unsatisfactory solution. This raises safety concerns in the network traffic field when previous class imbalance methods hardly deal with numerous minority malicious classes. To alleviate these effects, we design a group & reweight strategy for alleviating class imbalance. Inspired by the group distributionally optimization framework, our approach heuristically clusters classes into groups, iteratively updates the non-parametric weights for separate classes, and optimizes the learning model by minimizing reweighted losses. We theoretically interpret the optimization process from a Stackelberg game and perform extensive experiments on typical benchmarks. Results show that our approach can not only suppress the negative effect of class imbalance but also improve the comprehensive performance in prediction.