Channel-Token Attention for Reliable Dynamic Spectrum Access under Bursty Primary-User Traffic

We study the restless contextual multi-play multi-armed bandit (MP-MAB) problem for channel allocation in the opportunity spectrum access (OSA) scenario. Most existing MP-MAB methods are impractical for real-world OSA systems as they assume many ideal conditions, incur a heavy computational cost, and most importantly, ignore the impact of channel noise which is directly related to the quality of service. In this study, we embody this impact by modeling channel noise as a perturbation of the arm's reward function in MP-MAB. As there is an implicit correlation between channel state information and channel noise, we take the former as a context for MP-MAB to present the perturbation caused by the latter. We investigate two types of correlation between the context and the perturbation -- linear and nonlinear, and derive two index policies, respectively. These policies learn the correlations through a linear model and a neural network, and use estimated noise value to adjust the upper confidence bound. Numerical experiments demonstrate that the proposed policies can achieve lower regret and select sub-optimal arms in a more reasonable way.

Token communications (TokenCom) is an emerging generative semantic communication paradigm, where tokens serve as compact representation units across modalities. Their contextual dependencies can be exploited by pretrained large models for semantic recovery. In this paper, we propose token-domain multiple access (ToDMA), a large-model-driven semantic multiple access scheme for massive token communications. ToDMA integrates unsourced random access with context-aware token processing. It enables massive uncoordinated devices to transmit tokenized source representations over common uplink resources. Specifically, each token index is associated with a shared modulation codeword, exposing token-level structure to the receiver for context-aware recovery. At the receiver, compressed sensing is first employed to jointly detect active tokens and estimate their corresponding channel state information (CSI) from the superposed signals. The source token sequences are then reconstructed by exploiting the consistency of token-associated CSI across multiple token positions. In the presence of token collisions, some active tokens may remain unassigned, leading to missing entries in the reconstructed token sequences. To recover these tokens, candidate-restricted masked-token prediction is performed using pretrained contextual models, thereby leveraging token-level context to mitigate collision effects. Simulation results on both image and text transmission tasks demonstrate that ToDMA reduces access latency while maintaining favorable token recovery and semantic reconstruction quality, showing its scalability for semantic multiple access.

Integrated sensing and communication (ISAC) networks can serve compatible requests through shared sensing sessions, but consolidation couples admission, reuse, profile selection, sensing service-level agreements (SLAs), communication quality of service (QoS), and future commitments. We formulate this problem as a constrained Markov decision process and propose Common-Trace Factorized Constrained Proximal Policy Optimization (CT-PPO). During training, stochastic policy replicas share the same primitive workload trace; leave-one-out discounted Monte Carlo return contrasts provide reward credit to applicable actor factors, while constraint credit remains factor/prefix-specific. Across five training seeds and matched workloads, CT-PPO achieves the highest mean macro return, exceeding matched Joint-Credit PPO (JC-PPO) by 0.934 (95% confidence interval [0.702, 1.164]) and SLA-Aware Greedy by 1.847; versus JC-PPO, it reduces sensing-resource cost by 6.277 and raises accepted requests per created session by 0.0806. A four-way ablation shows that the factorized surrogate alone yields no detectable macro-return gain, whereas adding common-trace reward credit produces the dominant improvement. Without retraining, CT-PPO retains a return advantage at low, nominal, and high arrival loads, with the strongest gain under clustered arrivals. Deployment uses public observations and hard masks; CT-PPO's extra parameters are training-side, its actor footprint matches JC-PPO, and actor-only CPU latency is effectively unchanged.