Incremental Learning in Network Traffic Management: A Fixed-Representation Rehearsal Approach
Year: 2026
Type: conference-paper
Abstract: Network traffic management systems must continuously evolve to new applications without degrading the performance of previously learned categories. This paper evaluates a class-incremental learning strategy that combines rehearsalbased replay with fixed feature representation. Starting from a Fully Connected Neural Network (FCNN) trained on six traffic classes using flow-level features, we freeze all feature-extraction layers and retrain only a newly initialized classification head. Incremental updates are performed using all samples from the incoming class(es) plus a compact, stratified rehearsal buffer containing 10% of the original training set. Experiments on 46,729 labeled flows assess two scenarios: adding one class and adding two classes, and compare against full retraining as an upper bound. The proposed approach reaches 87.90% and 87.72% test accuracy (weighted F1 of 0.877 and 0.875) with minimal forgetting (gaps up to$\mathbf{1. 1 3 \%})$. Incremental updates reduce training time by 89-92% and decrease training-data storage requirements by up to 76.88%, supporting deployment in dynamic network environments.
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7204104558