Uncertainty-Aware Federated Learning for Joint Communication and Computation in XR Systems
Abstract
The convergence of communication and computation, empowered by artificial intelligence (AI) enhanced capabilities, emerges as a key enabler for realizing the promising functionalities of the sixth-generation of communication systems (6G). To this end, this paper investigates an AI-native, robust network, where multiple base stations (BSs) simultaneously serve several extended reality (XR) devices. The paper then presents an innovative distributed deep learning-based approach to simultaneously manage the transmit and computing powers, and computation allocation, amidst uncertainties in both channel and computing states information. Under such an interference network scenario, the paper proposes a robust approach for minimizing the worst-case delay across the served XR devices, subject to computation and power constraints. The paper leverages a deep neural network (DNN) that can be trained either centrally or in a federated manner to map estimated channels and computation requirements to optimized resource allocations per BS. During training, uncertainty samples, reflecting both channel and computing estimation errors, are injected after the DNN output to account for such joint uncertainties. Our results validate the enhanced robust delay performance and scalability of joint uncertainty injection as compared to uncertainty-agnostic methods and state-of-the-art benchmarks, with federated learning-based solutions achieving near-centralized performance while enhancing efficiency, privacy, and adaptability.
Versions
Related
- Federated Calibration of Motion Uncertainty for UAV Tracking in Multi-Operator ISAC Systems
- Federated learning with heavy-tailed gradient noise and communication noise: a variance-reduction based algorithm
- Provably Efficient Federated Reinforcement Learning with Linear Function Approximation and Logarithmic Communication Cost
- CRB-Guided Sensing and Resource Allocation for Human Pose Prediction in Integrated Sensing, Communication, and Computation Systems
- Learning OTA: A Unified Framework for Edge Sensing, Computation, and Communication
BibTeX
@misc{reifert2026uncertaintyaware,
title = {{Uncertainty-Aware Federated Learning for Joint Communication and Computation in XR Systems}},
author = {Robert-Jeron Reifert and Hayssam Dahrouj and Alaa Alameer Ahmad and Haris Gacanin and Aydin Sezgin},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.21969},
eprint = {2610.21969},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.21969},
}
RIS
TY - UNPB
TI - Uncertainty-Aware Federated Learning for Joint Communication and Computation in XR Systems
AU - Robert-Jeron Reifert
AU - Hayssam Dahrouj
AU - Alaa Alameer Ahmad
AU - Haris Gacanin
AU - Aydin Sezgin
PY - 2026
DA - 2026/10/15
PB - arXiv
DO - 10.48550/arxiv.2610.21969
UR - https://arxiv.org/abs/2610.21969
AB - The convergence of communication and computation, empowered by artificial intelligence (AI) enhanced capabilities, emerges as a key enabler for realizing the promising functionalities of the sixth-generation of communication systems (6G). To this end, this paper investigates an AI-native, robust network, where multiple base stations (BSs) simultaneously serve several extended reality (XR) devices. The paper then presents an innovative distributed deep learning-based approach to simultaneously manage the transmit and computing powers, and computation allocation, amidst uncertainties in both channel and computing states information. Under such an interference network scenario, the paper proposes a robust approach for minimizing the worst-case delay across the served XR devices, subject to computation and power constraints. The paper leverages a deep neural network (DNN) that can be trained either centrally or in a federated manner to map estimated channels and computation requirements to optimized resource allocations per BS. During training, uncertainty samples, reflecting both channel and computing estimation errors, are injected after the DNN output to account for such joint uncertainties. Our results validate the enhanced robust delay performance and scalability of joint uncertainty injection as compared to uncertainty-agnostic methods and state-of-the-art benchmarks, with federated learning-based solutions achieving near-centralized performance while enhancing efficiency, privacy, and adaptability.
ER -