Edge-Assisted Data Selection and Continuous Training Framework for AI Services Under Resource-Constrained Networks

The shift to virtual networks has facilitated the use of deep learning (DL) models for flexible, real-time AI services across various applications. However, to maintain inference accuracy and Quality-of-Service (QoS), these models need regular retraining as data patterns change over time, such as the appearance of new classes or changes in feature distributions. Continuous edge-assisted retraining reduces the communication cost to the cloud, however, it remains limited by network constraints. To address these issues, this paper introduces a Balanced Data Selection (BDS) algorithm, which reduces data imbalance and improves retraining accuracy within resource-constrained environments. BDS offers a low-complexity solution that scales efficiently with the size of new data. Furthermore, we introduce a continuous training framework that supports both data and class incremental learning. Experimental results indicate that our framework achieves retraining accuracy that is superior to baseline solutions, while maintaining lower complexity and effectively addressing data imbalance. This framework provides an effective approach for edge-assisted DL model retraining.