# Domain Adaptation Under Wireless Network Constraints: When Does It Become Green?

arXiv: https://arxiv.org/abs/2606.23047 · HTML: https://mlsanity.com/paper/2606.23047/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 31 references that are in the map.
- First posted on arXiv 22 Jun 2026.

## Builds on (most cited first, 15 of 15)

- [Energy and Policy Considerations for Deep Learning in NLP](https://mlsanity.com/paper/1906.02243/) (2019)
- [Carbon Emissions and Large Neural Network Training](https://mlsanity.com/paper/2104.10350/) (2021)
- [Quantifying the Carbon Emissions of Machine Learning](https://mlsanity.com/paper/1910.09700/) (2019)
- [Sustainable AI: Environmental Implications, Challenges and Opportunities](https://mlsanity.com/paper/2111.00364/) (2021)
- [An Introduction to Deep Learning for the Physical Layer](https://mlsanity.com/paper/1702.00832/) (2017)
- [On-Device Training Under 256KB Memory](https://mlsanity.com/paper/2206.15472/) (2022)
- [Learning to Optimize: Training Deep Neural Networks for Wireless Resource Management](https://mlsanity.com/paper/1705.09412/) (2017)
- [Eco2AI: carbon emissions tracking of machine learning models as the first step towards sustainable AI](https://mlsanity.com/paper/2208.00406/) (2022)
- [Large Language Models for Telecom: Forthcoming Impact on the Industry](https://mlsanity.com/paper/2308.06013/) (2023)
- [AI based Service Management for 6G Green Communications](https://mlsanity.com/paper/2101.01588/) (2021)
- [A Survey of Energy-Efficient Techniques for 5G Networks and Challenges Ahead](https://mlsanity.com/paper/1604.00786/) (2016)
- [Optimizing Information Freshness in Wireless Networks under General Interference Constraints](https://mlsanity.com/paper/1803.06467/) (2018)
- [Few-Shot Domain Adaptation For End-to-End Communication](https://mlsanity.com/paper/2108.00874/) (2021)
- [Deep Unsupervised Domain Adaptation for Time Series Classification: a Benchmark](https://mlsanity.com/paper/2312.09857/) (2023)
- [Through the telecom lens: Are all training samples important?](https://mlsanity.com/paper/2511.21668/) (2025)

## Abstract (arXiv)

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.