# Automatic AI Model Selection for Wireless Systems: Online Learning via Digital Twinning

arXiv: https://arxiv.org/abs/2406.15819 · HTML: https://mlsanity.com/paper/2406.15819/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 48 references that are in the map.
- First posted on arXiv 22 Jun 2024.

## Builds on (most cited first, 30 of 35)

- [Meta-Learning in Neural Networks: A Survey](https://mlsanity.com/paper/2004.05439/) (2020)
- [On the Variance of the Adaptive Learning Rate and Beyond](https://mlsanity.com/paper/1908.03265/) (2019)
- [Domain Generalization: A Survey](https://mlsanity.com/paper/2103.02503/) (2021)
- [Prediction-Powered Inference](https://mlsanity.com/paper/2301.09633/) (2023)
- [A Review of Generalized Zero-Shot Learning Methods](https://mlsanity.com/paper/2011.08641/) (2020)
- [PPI++: Efficient Prediction-Powered Inference](https://mlsanity.com/paper/2311.01453/) (2023)
- [A Brief Review of Hypernetworks in Deep Learning](https://mlsanity.com/paper/2306.06955/) (2023)
- [Optimal Wireless Resource Allocation with Random Edge Graph Neural Networks](https://mlsanity.com/paper/1909.01865/) (2019)
- [Graph Neural Networks for Scalable Radio Resource Management: Architecture Design and Theoretical Analysis](https://mlsanity.com/paper/2007.07632/) (2020)
- [Understanding O-RAN: Architecture, Interfaces, Algorithms, Security, and Research Challenges](https://mlsanity.com/paper/2202.01032/) (2022)
- [Digital Twin of Wireless Systems: Overview, Taxonomy, Challenges, and Opportunities](https://mlsanity.com/paper/2202.02559/) (2022)
- [A Guide Through the Zoo of Biased SGD](https://mlsanity.com/paper/2305.16296/) (2023)
- [Graph Embedding based Wireless Link Scheduling with Few Training Samples](https://mlsanity.com/paper/1906.02871/) (2019)
- [Conformal Validity Guarantees Exist for Any Data Distribution (and How to Find Them)](https://mlsanity.com/paper/2405.06627/) (2024)
- [From Learning to Meta-Learning: Reduced Training Overhead and Complexity for Communication Systems](https://mlsanity.com/paper/2001.01227/) (2020)
- [A Bayesian Framework for Digital Twin-Based Control, Monitoring, and Data Collection in Wireless Systems](https://mlsanity.com/paper/2212.01351/) (2022)
- [Doubly Robust Self-Training](https://mlsanity.com/paper/2306.00265/) (2023)
- [Calibrating Wireless Ray Tracing for Digital Twinning using Local Phase Error Estimates](https://mlsanity.com/paper/2312.12625/) (2023)
- [Modular Meta-Learning for Power Control via Random Edge Graph Neural Networks](https://mlsanity.com/paper/2108.13178/) (2021)
- [Edge Continual Learning for Dynamic Digital Twins over Wireless Networks](https://mlsanity.com/paper/2204.04795/) (2022)
- [Towards a Decentralized Metaverse: Synchronized Orchestration of Digital Twins and Sub-Metaverses](https://mlsanity.com/paper/2211.14686/) (2022)
- [Digital Twin Based Beam Prediction: Can we Train in the Digital World and Deploy in Reality?](https://mlsanity.com/paper/2301.07682/) (2023)
- [Cell-Free Multi-User MIMO Equalization via In-Context Learning](https://mlsanity.com/paper/2404.05538/) (2024)
- [Neuromorphic Split Computing with Wake-Up Radios: Architecture and Design via Digital Twinning](https://mlsanity.com/paper/2404.01815/) (2024)
- [Colosseum as a Digital Twin: Bridging Real-World Experimentation and Wireless Network Emulation](https://mlsanity.com/paper/2303.17063/) (2023)
- [Multiverse at the Edge: Interacting Real World and Digital Twins for Wireless Beamforming](https://mlsanity.com/paper/2305.10350/) (2023)
- [Energy Efficient Computation Offloading in Aerial Edge Networks With Multi-Agent Cooperation](https://mlsanity.com/paper/2302.09021/) (2023)
- [Meta-Gating Framework for Fast and Continuous Resource Optimization in Dynamic Wireless Environments](https://mlsanity.com/paper/2306.13277/) (2023)
- [What-if Analysis Framework for Digital Twins in 6G Wireless Network Management](https://mlsanity.com/paper/2404.11394/) (2024)
- [Digital Twin Aided Massive MIMO: CSI Compression and Feedback](https://mlsanity.com/paper/2402.19434/) (2024)

## Built on by (most cited first, 3 of 3)

- [What If We Had Used a Different App? Reliable Counterfactual KPI Analysis in Wireless Systems](https://mlsanity.com/paper/2410.00150/) (2024)
- [Context-Aware Doubly-Robust Semi-Supervised Learning](https://mlsanity.com/paper/2502.15577/) (2025)
- [Reliable Wireless Indoor Localization via Cross-Validated Prediction-Powered Calibration](https://mlsanity.com/paper/2507.20268/) (2025)

## Abstract (arXiv)

In modern wireless network architectures, such as O-RAN, artificial intelligence (AI)-based applications are deployed at intelligent controllers to carry out functionalities like scheduling or power control. The AI "apps" are selected on the basis of contextual information such as network conditions, topology, traffic statistics, and design goals. The mapping between context and AI model parameters is ideally done in a zero-shot fashion via an automatic model selection (AMS) mapping that leverages only contextual information without requiring any current data. This paper introduces a general methodology for the online optimization of AMS mappings. Optimizing an AMS mapping is challenging, as it requires exposure to data collected from many different contexts. Therefore, if carried out online, this initial optimization phase would be extremely time consuming. A possible solution is to leverage a digital twin of the physical system to generate synthetic data from multiple simulated contexts. However, given that the simulator at the digital twin is imperfect, a direct use of simulated data for the optimization of the AMS mapping would yield poor performance when tested in the real system. This paper proposes a novel method for the online optimization of AMS mapping that corrects for the bias of the simulator by means of limited real data collected from the physical system. Experimental results for a graph neural network-based power control app demonstrate the significant advantages of the proposed approach.