19 February 2025 in IEEE Wireless Communications Letters
In this letter, we use large language models (LLMs) to develop a high-performing and robust beam prediction method. We formulate the millimeter wave (mmWave) beam prediction problem as a time series forecasting task, where the historical observations are aggregated through cross-variable attention and then transformed into text-based representations using a trainable tokenizer. By leveraging the prompt-as-prefix (PaP) technique for contextual enrichment, our method harnesses the power of LLMs to predict future optimal beams. Simulation results demonstrate that our LLM-based approach outperforms traditional learning-based models in prediction accuracy as well as robustness, highlighting the significant potential of LLMs in enhancing wireless communication systems.
17 March 2025 in IEEE Transactions on Communications
In this paper, we consider a radio resource management (RRM) problem in the dynamic wireless networks, comprising multiple communication links that share the same spectrum resource. To achieve high network throughput while ensuring fairness across all links, we formulate a resilient power optimization problem with per-user minimum-rate constraints. We obtain the corresponding Lagrangian dual problem and parameterize all variables with neural networks, which can be trained in an unsupervised manner due to the provably acceptable duality gap. We develop a meta-learning approach with graph neural networks (GNNs) as parameterization that exhibits fast adaptation and scalability to varying network configurations. We formulate the objective of meta-learning by amalgamating the Lagrangian functions of different network configurations and utilize a first-order meta-learning algorithm, called Reptile, to obtain the meta-parameters. Numerical results verify that our method can efficiently improve the overall throughput and ensure the minimum rate performance. We further demonstrate that using the meta-parameters as initialization, our method can achieve fast adaptation to new wireless network configurations and reduce the number of required training data samples.
6 June 2025 in IEEE Transactions on Vehicular Technology
The pursuit of rate maximization in wireless communication frequently encounters substantial challenges associated with user fairness. This paper addresses these challenges by exploring a novel power allocation approach for delay optimization, utilizing graph neural networks (GNNs)-based reinforcement learning (RL) in device-to-device (D2D) communication. The proposed approach incorporates not only channel state information but also factors such as packet delay, the number of backlogged packets, and the number of transmitted packets into the components of the state information. We adopt a centralized RL method, where a central controller collects and processes the state information. The central controller functions as an agent trained using the proximal policy optimization (PPO) algorithm. To better utilize topology information in the communication network and enhance the generalization of the proposed method, we embed GNN layers into both the actor and critic networks of the PPO algorithm. This integration allows for efficient parameter updates of GNNs and enables the state information to be parameterized as a low-dimensional embedding, which is leveraged by the agent to optimize power allocation strategies. Simulation results demonstrate that the proposed method effectively reduces average delay while ensuring user fairness, outperforms baseline methods, and exhibits scalability and generalization capability.
15 October 2025 in IEEE Wireless Communications Letters
In this letter, we propose a meta-learning-based fast adversarial training method to address the vulnerability of graph neural network (GNN) based resource allocation method to adversarial attacks. For a specific wireless network configuration, we design a convolutional neural network (CNN) based adversarial generator and perform adversarial training with the generated samples. Besides, we utilize a context-based meta-learning method to improve generalization of the adversarial training method across different configurations. Simulation results demonstrate that the proposed method can effectively accelerate the adversarial training process and reduce the required training samples, which is promising for enhancing the robustness of learning-based resource allocation schemes.