Domain Adaptation Under Wireless Network Constraints: When Does It Become Green?
This work provides practical guidance for network operators on when to choose UDA over retraining to balance energy and labeling costs.
The paper investigates the energy consumption of Unsupervised Domain Adaptation (UDA) compared to retraining in 6G wireless networks, and determines the minimum number of target domains where UDA becomes more energy-efficient when labeling cost is considered.
The deployment of data-driven models in 6G wireless networks is increasingly challenged by frequent distribution shifts that degrade performance over time. Unsupervised Domain Adaptation (UDA) offers an alternative approach by adapting the trained model to a shifted domain without requiring labels. However, UDA pipelines are often more complex than single-task training due to additional modules and optimization procedures, raising a practical question: do the benefits of adaptation come at a higher energy cost, and how does this trade-off compare to retraining when labeling effort is also considered? In this work, we investigate the energy consumption of UDA and compare it to single task. We further propose a way to determine the minimum number of target domains for which UDA becomes more energy-efficient than retraining, taking into account the labeling cost. Our results aim to clarify when UDA should be preferred over classical train-from-scratch approaches from an energy and labeling-aware perspective.