analiza aiqbench
This paper introduces FedSSL-AMC, a federated self-supervised framework designed to train automatic modulation classifiers on distributed I/Q data without central aggregation. By leveraging triplet-loss self-supervision and lightweight local SVMs, the method effectively addresses challenges like non-IID distributions, class imbalance, and communication overhead at the network edge. Theoretical convergence guarantees combined with experimental results demonstrate robust performance across heterogeneous signal conditions, advancing practical cognitive wireless systems.
Federated Self-Supervised Modulation Classification under Non-IID and Imbalanced Data
arXiv:2510.04927v2 Announce Type: replace Abstract: Automatic modulation classification (AMC) is a core enabler of cognitive wireless systems, providing spectrum awareness and supporting adaptive communication at the network edge. However, training AMC models on centrally aggregated data incurs high communication overhead, raises privacy concerns, and often lacks robustness to real-world conditions. We propose FedSSL-AMC, a federated self-supervised framework for learning AMC models from sparsely labeled, distributed I/Q time-series data. Participating clients collaboratively train a causal, time-dilated CNN encoder using triplet-loss self-supervision on unlabeled signals, followed by lightweight local SVMs trained on limited labeled samples. This enables communication-round-efficient, robust representation learning under class imbalance and channel variability. We establish convergence guarantees for a proximal variant of the encoder-training procedure and derive a separability bound for the downstream classifier under feature noise. Experiments on synthetic and over-the-air datasets demonstrate improvements over supervised FL baselines across all three datasets and nearly all evaluated settings involving heterogeneous SNRs, carrier-frequency offsets, and non-IID label distributions.
Abstract:Automatic modulation classification (AMC) is a core enabler of cognitive wireless systems, providing spectrum awareness and supporting adaptive communication at the network edge. However, training AMC models on centrally aggregated data incurs high communication overhead, raises privacy concerns, and often lacks robustness to real-world conditions. We propose FedSSL-AMC, a federated self-supervised framework for learning AMC models from sparsely labeled, distributed I/Q time-series data. Participating clients collaboratively train a causal, time-dilated CNN encoder using triplet-loss self-supervision on unlabeled signals, followed by lightweight local SVMs trained on limited labeled samples. This enables communication-round-efficient, robust representation learning under class imbalance and channel variability. We establish convergence guarantees for a proximal variant of the encoder-training procedure and derive a separability bound for the downstream classifier under feature noise. Experiments on synthetic and over-the-air datasets demonstrate improvements over supervised FL baselines across all three datasets and nearly all evaluated settings involving heterogeneous SNRs, carrier-frequency offsets, and non-IID label distributions.
Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Signal Processing (eess.SP)
arXiv:2510.04927 [cs.LG]
(or arXiv:2510.04927v2 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2510.04927 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 252 cuvinte
Subiecte conexe
Rivian’s Gambit for Full Autonomy
IEEE Spectrum · 8 sept. 2026
Why Does Graph Learning Fail to Fully Benefit from a Text Teacher?
arXiv · 27 aug. 2026
Attention-Only White-Box Transformer via LeJEPA-Based Self-Supervised Pretraining
arXiv · 6 aug. 2026
Why I Left Google DeepMind
LessWrong · 15 iul. 2026