Semantic communications aim to enhance transmission efficiency by jointly optimizing source coding, channel coding, and modulation. While prior research has demonstrated promising performance in simulations, real-world implementations often face significant challenges, including noise variability and nonlinear distortions, leading to performance gaps. This article investigates these challenges in a multiple-input multiple-output (MIMO) and orthogonal frequency division multiplexing (OFDM)-based semantic communication system, focusing on the practical impacts of power amplifier (PA) nonlinearity and peak-to-average power ratio (PAPR) variations. Our analysis identifies frequency selectivity of the actual channel as a critical factor in performance degradation and demonstrates that targeted mitigation strategies can enable semantic systems to approach theoretical performance. By addressing key limitations in existing designs, we provide actionable insights for advancing semantic communications in practical wireless environments. This work establishes a foundation for bridging the gap between theoretical models and real-world deployment, highlighting essential considerations for system design and optimization.

For instance, FedProx [Li et al., 2020] controls Federated learning are inherently hampered by data the number of iterations for each local device, aiming to heterogeneity: non-iid distributed training data train models resilient to challenges posed by non-independent over local clients. We propose a novel model training and non-iid data environments. SCAFFOLD [Karimireddy approach for federated learning, FLex&Chill, et al., 2020] achieves expedited convergence and improved which exploits the Logit Chilling method. Through model accuracy [McMahan et al., 2017] by introducing a extensive evaluations, we demonstrate that, in the correction term during the model aggregation phase to balance presence of non-iid data characteristics inherent in the influence of each client. These operations alleviate federated learning systems, this approach can expedite the problems posed by the non-iid environment, a common model convergence and improve inference accuracy.

Bayesian neural networks (BNNs) have shown success in the areas of uncertainty estimation and robustness. However, a crucial challenge prohibits their use in practice: Bayesian NNs require a large number of predictions to produce reliable results, leading to a significant increase in computational cost. To alleviate this issue, we propose spatial smoothing, a method that ensembles neighboring feature map points of CNNs. By simply adding a few blur layers to the models, we empirically show that the spatial smoothing improves accuracy, uncertainty estimation, and robustness of BNNs across a whole range of ensemble sizes. In particular, BNNs incorporating the spatial smoothing achieve high predictive performance merely with a handful of ensembles. Moreover, this method also can be applied to canonical deterministic neural networks to improve the performances. A number of evidences suggest that the improvements can be attributed to the smoothing and flattening of the loss landscape. In addition, we provide a fundamental explanation for prior works - namely, global average pooling, pre-activation, and ReLU6 - by addressing to them as special cases of the spatial smoothing. These not only enhance accuracy, but also improve uncertainty estimation and robustness by making the loss landscape smoother in the same manner as the spatial smoothing. The code is available at https://github.com/xxxnell/spatial-smoothing.

While deep neural networks (NNs) do not provide the confidence of its prediction, Bayesian neural network (BNN) can estimate the uncertainty of the prediction. However, BNNs have not been widely used in practice due to the computational cost of inference. This prohibitive computational cost is a hindrance especially when processing stream data with low-latency. To address this problem, we propose a novel model which approximate BNNs for data streams. Instead of generating separate prediction for each data sample independently, this model estimates the increments of prediction for a new data sample from the previous predictions. The computational cost of this model is almost the same as that of non-Bayesian NNs. Experiments with semantic segmentation on real-world data show that this model performs significantly faster than BNNs, estimating uncertainty comparable to the results of BNNs.