Abstract
In the context of the proliferated evolution of network service types and the expeditious augmentation of network resource deployment, the requisition for copious labeled datasets to facilitate superior performance in traffic classification methods, particularly those hinging on deep learning, is imperative. Nonetheless, the procurement and annotation of such extensive datasets necessitate considerable temporal and human resource investments. In response to this predicament, this work introduces a methodology, termed MTEFU, leveraging a deep learning model-based multi-task learning algorithm, strategically designed to mitigate the reliance on substantial labeled training samples. Multiple classification tasks, encompassing duration, bandwidth size, and business traffic category, are incorporated, with a shared parameter strategy implemented amongst tasks to assure the transference of information across disparate tasks. Employing CNN, SAE, GRU, and LSTM as multi-task learning classification models, training validation and experimental testing were conducted on the QUIC dataset. A comparative analysis with single-task and ensemble learning methods reveals that, in the context of predicting network traffic types, the accuracy derived from the multi-task learning strategy, even with a mere 150 labeled samples, can emulate the 94.67% accuracy achieved through single-task learning with a fully labeled dataset of 6139 samples.