Semantic communications have emerged as a new communication paradigm that extracts and transmits meaningful information relevant to receiver tasks. The trendy semantic coding framework, namely, learning-based joint source-channel coding (JSCC), lies on data-driven principles, with its efficacy depending on the employed neural networks (NNs). This paper introduces a codebook-assisted semantic coding method to improve JSCC performance for image transmission. Notably, a well-constructed codebook is employed to map each source image into a codeword, which subsequently provides shared prior information to assist semantic coding with general NN architectures. The main novelty is two-fold. First, we propose a general semantic-aware codebook construction method based on weighted data-semantic distance. In the case where the semantic information is characterized by discrete labels, this method is refined by encapsulating the labels into codeword indexes. Second, we derive a novel information-theoretic loss function via variational approximation for end-to-end training of the semantic encoder and decoder. This loss function includes a penalty term to mitigate redundancy in the received signals concerning codewords. Extensive experiments conducted over both additive noisy channels and fading channels validate the superior performance of the proposed method with even small-sized codebooks in both image reconstruction and classification accuracy.

Federated multi-task learning (FMTL) is a promising edge learning framework to fit the data with non-independent and non-identical distribution (non-i.i.d.) by leveraging the statistical correlations among the personalized models. For many practical applications in wireless communications, the sensory data are not only heterogeneous but also non-stationary due to the mobility of terminals and the randomness of link connections. The non-stationary heterogeneous data may lead to model divergence and staleness in the training stage and poor test accuracy in the inference stage. In this paper, we shall develop an adaptive FMTL framework, which works well with non-stationary data. We further propose to optimize the model updating and cluster splitting schemes in the training stage to accelerate model convergence. We also design a low-complexity model selection and pruning schemes in both the training and inference stages to select the best model for fitting the current data and delete redundant models, respectively. The proposed framework is validated in the edge learning model, namely, the linear regression problem for indoor localization in wireless networks and GNN for wireless power control problems. Numerical results demonstrate that the proposed framework can accelerate the model training convergence and reduce the computation complexity while ensuring model accuracy.

Existing deep learning-enabled semantic communication systems often rely on shared background knowledge between the transmitter and receiver that includes empirical data and their associated semantic information. In practice, the semantic information is defined by the pragmatic task of the receiver and cannot be known to the transmitter. The actual observable data at the transmitter can also have non-identical distribution with the empirical data in the shared background knowledge library. To address these practical issues, this paper proposes a new neural network-based semantic communication system for image transmission, where the task is unaware at the transmitter and the data environment is dynamic. The system consists of two main parts, namely the semantic coding (SC) network and the data adaptation (DA) network. The SC network learns how to extract and transmit the semantic information using a receiver-leading training process. By using the domain adaptation technique from transfer learning, the DA network learns how to convert the data observed into a similar form of the empirical data that the SC network can process without re-training. Numerical experiments show that the proposed method can be adaptive to observable datasets while keeping high performance in terms of both data recovery and task execution.

Federated multi-task learning (FMTL) is a promising edge learning framework to fit the data with non-independent and non-identical distribution (non-i.i.d.) by exploiting the correlations of personalized models. In many practical systems, the sensory data distribution in wireless systems is not only heterogeneous but also non-stationary due to the mobility of terminals and the randomness of link connections. The non-stationary heterogeneous data may lead to model divergence and staleness in the training stage and poor accuracy in the inference stage. In this paper, we design an adaptive FMTL framework, which can work in a non-stationary environment. We propose to optimize the model update scheme and cluster splitting scheme in the training stage to accelerate model convergencse when the training data are non-stationary. We further design a low-complexity model selection scheme in both the training and the inference stages to choose the best model for fitting the current data. The proposed framework is validated in two scenarios, linear regression and graph neural network (GNN)-based power control in wireless device-to-device (D2D) networks. Both sets of numerical results demonstrate that the proposed framework can accelerate the model training convergence and reduce the computation complexity while ensuring model accuracy.