Learning to Optimize Joint Source and RIS-assisted Channel Encoding for Multi-User Semantic Communication Systems
Authors: Haidong Wang, Songhan Zhao, Bo Gu, Shimin Gong, Hongyang Du, Ping Wang
Organizations: School of Intelligent Systems Engineering, Sun Yat-sen University, China · Department of Electrical and Computer Engineering, University of Hong Kong, HongKong, SAR, China · Department of Electrical Engineering and Computer Science, Lassonde School of Engineering, York University, Canada
In this paper, we explore a joint source and reconfigurable intelligent surface (RIS)-assisted channel encoding (JSRE) framework for multi-user semantic communications, where a deep neural network (DNN) extracts semantic features for all users and the RIS provides channel orthogonality, enabling a unified semantic encoding-decoding design. We aim to maximize the overall energy efficiency of semantic communications across all users by jointly optimizing the user scheduling, the RIS's phase shifts, and the semantic compression ratio. Although this joint optimization problem can be addressed using conventional deep reinforcement learning (DRL) methods, evaluating semantic similarity typically relies on extensive real environment interactions, which can incur heavy computational overhead during training. To address this challenge, we propose a truncated DRL (T-DRL) framework, where a DNN-based semantic similarity estimator is developed to rapidly estimate the similarity score. Moreover, the user scheduling strategy is tightly coupled with the semantic model configuration. To exploit this relationship, we further propose a semantic model caching mechanism that stores and reuses fine-tuned semantic models corresponding to different scheduling decisions. A Transformer-based actor network is employed within the DRL framework to dynamically generate action space conditioned on the current caching state. This avoids redundant retraining and further accelerates the convergence of the learning process. Numerical results demonstrate that the proposed JSRE framework significantly improves the system energy efficiency compared with the baseline methods. By training fewer semantic models, the proposed T-DRL framework significantly enhances the learning efficiency.
Figures & tables
Fig. 1: The multi-band RIS-assisted multi-user semantic transmissions.
Fig. 2: The JSRE’s network architecture for semantic encoder and decoder shared by all users.
Fig. 3: The T-DRL framework with fast reward estimator and model caching.
Fig. 4: Transformer-based actor network for truncatable decision making.
Parameters
Settings
Number of users K
5
Transmit power pd
40 dBm
Background noise power σ2
−174 dBm/Hz
Rician factor
10
Pathloss model
128.1+37.6log(d) dB
Sub-band bandwidth Wc
20 MHz
TABLE I: Parameter settings in the simulation.
Fig. 5: The coding efficiency under various environmental settings.
Fig. 6: Visual reconstruction quality under the JSRE framework
Fig. 7: Convergence performance of different DRL and parameters
Variants
Duration
Converge step ( ×103 )
Energy efficiency (suts/J)
T-DRL
6h 11m
21.19
5.52
T-DRL w/o truncation
8h 33m
36.14
5.27
T-DRL w/o estimator
9h 08m
15.32
5.42
T-DRL w/o caching
20h 18m
15.54
5.50
TABLE II: Comparison T-DRL variants.
Fig. 8: System performance under different RIS sizes.
Fig. 9: Energy efficiency under different numbers of users.
Efficient resource utilization is proposed for simultaneously transmitting and reflecting reconfigurable intelligent surfaces (STAR-RIS) to ensure fair and high data rates. We optimize the number of STAR-RIS elements to be allocated to each user and maximize the sum of the user rates. To promote fairness, we introduce a soft fairness mechanism that guarantees a minimum STAR-RIS element allocation to every user. Subject to this requirement, the phase shifts of the STAR-RIS elements and the remaining element assignments are jointly optimized by harnessing an appropriately tailored deep reinforcement learning (DRL) algorithm. The proposed DRL method is also compared to Dinkelbach's algorithm and to a bespoke hybrid DRL approach. A deactivation incentive is incorporated into the DRL model for enhancing resource utilization by intelligently deactivating some of the STAR-RIS elements when not required. The proposed DRL method achieves fair and high data rates for both stationary and mobile users, while ensuring efficient resource utilization. Using the proposed DRL method, up to 34% and 23% of STAR-RIS elements can be deactivated in static and mobile scenarios, respectively, with negligible degradation in the average DL data rate.
Ashok S. Kumar, Nancy Nayak, Sheetal Kalyani +2
Department of Electrical Engineering, Indian Institute of Technology Madras, Chennai, India · Department of Electrical and Electronic Engineering, Imperial College London, United Kingdom · Department of Electrical and Electronic Engineering, University of Peradeniya, Peradeniya 20400, Sri Lanka +1
This paper studies energy efficient tracking of power-limited mobile users with the assistance of a Reconfigurable Intelligent Surface (RIS). Since localization pilot transmissions dominate the energy budget of power-constrained devices, we introduce a low-overhead feedback link from the Base Station (BS) to the user to enable dynamic uplink power control. To navigate the discrete and decentralized nature of this active sensing problem, we propose a novel Dual-Agent (DA) deep learning framework that jointly optimizes the discrete RIS phase profiles and the UE's transmit power in real time. Specifically, our approach employs a hybrid training methodology integrating the neuroevolution paradigm with supervised learning, effectively overcoming the non-differentiability of discrete phase responses from the RIS unit elements and the strict information bottleneck of single-bit feedback messages for pilot power control. The proposed DA active sensing framework can be applied with both single- and multi-antenna BSs, the latter with only minor modifications in the structure of one NN: an additional output branch with appropriate structure is included for the latter case to select a valid digital combiner from a finite set. Extensive numerical simulations demonstrate that the proposed scheme achieves highly accurate and robust tracking across diverse target motion models, outperforming extended Kalman and particle filters, as well as, machine learning-based trackers. Furthermore, in static localization, it is shown to significantly outperform traditional fingerprinting schemes, deep reinforcement learning baselines, and standard backpropagation-based estimators.
George Stamatelis, Hui Chen, Henk Henk Wymeersch +1
Department of Informatics and Telecommunications, National and Kapodistrian University of Athens, Panepistimiopolis Ilissia, 16122 Athens, Greece · Department of Electrical Engineering, Chalmers University of Technology, 412 58 Gothenburg, Sweden
Semantic communication (SemCom) with learned encoder-decoder architectures enables end-to-end learning of compact task-oriented representations optimized for the wireless channel, reducing channel resources needed to convey task-relevant information and improving spectrum efficiency. This paper studies semantic image transmission over block Rayleigh fading with AWGN using a multi-task semantic autoencoder that jointly reconstructs images and predicts labels from the received waveform. The latent dimension (complex channel uses per source sample) serves as a cross-layer control variable governing semantic fidelity and channel resource usage. We characterize the resulting latency-task fidelity tradeoff: larger latent representations improve inference accuracy but increase service time, channel uses, and queueing delay. Building on this insight, we develop online semantic-rate controllers that adapt the latent dimension per update under a long-term semantic error constraint. A queue-aware drift-plus-penalty policy minimizes delay subject to an average semantic error cap, while a complementary age-aware policy minimizes time-average Age of Information (AoI). By adapting the semantic rate to congestion and fidelity requirements, the proposed framework improves spectrum utilization and enables timely semantic updates with significantly lower delay and AoI than fixed-rate baselines.