Jingping Liu, Ziyan Liu, Zhedong Cen, Yan Zhou, Yinan Zou, Weiyan Zhang, Haiyun Jiang, Tong Ruan. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Cooperative localization leverages noisy inter-node distance measurements and exchanged wireless messages to estimate node positions in a wireless network. In communicationconstrained environments, however, transmitting large messages becomes problematic. In this paper, we propose an approach for communication-efficient cooperative localization that addresses two main challenges. First, cooperative localization often needs to be performed over wireless networks with loopy graph topologies. Second is the need for designing an algorithm that has low localization error while simultaneously requiring a much lower communication overhead. Existing methods fall short of addressing these two challenges concurrently. To achieve this, we propose a vector quantized message passing neural network (VQ-MPNN) for cooperative localization. Through end-to-end neural network training, VQ-MPNN enables the co-design of node localization and message compression. Specifically, VQMPNN treats prior node positions and distance measurements as node and edge features, respectively, which are encoded as node and edge states using a graph neural network. To find an efficient representation for the node state, we construct a vector quantized codebook for all node states such that instead of sending long messages, each node only needs to transmit a codeword index. Numerical evaluations demonstrates that our proposed VQ-MPNN approach can deliver localization errors that are similar to existing approaches while reducing the overall communication overhead by an order of magnitude.

Grant-free random access is an effective technology for enabling low-overhead and low-latency massive access, where joint activity detection and channel estimation (JADCE) is a critical issue. Although existing compressed sensing algorithms can be applied for JADCE, they usually fail to simultaneously harvest the following properties: effective sparsity inducing, fast convergence, robust to different pilot sequences, and adaptive to time-varying networks. To this end, we propose an unfolding framework for JADCE based on the proximal gradient method. Specifically, we formulate the JADCE problem as a group-row-sparse matrix recovery problem and leverage a minimax concave penalty rather than the widely-used$\ell _{1}$-norm to induce sparsity. We then develop a proximal gradient-based unfolding neural network that parameterizes the algorithmic iterations. To improve convergence rate, we incorporate momentum into the unfolding neural network, and prove the accelerated convergence theoretically. Based on the convergence analysis, we further develop an adaptive-tuning algorithm, which adjusts its parameters to different signal-to-noise ratio settings. Simulations show that the proposed unfolding neural network achieves better recovery performance, convergence rate, and adaptivity than current baselines.

Over-the-air federated learning (FL) is a promising privacy-preserving edge artificial intelligence paradigm, where over-the-air computation enables spectral-efficient model aggregation by achieving simultaneous communication and aggregation. However, due to limited transmit power, the performance of over-the-air FL is limited by the device with the worst channel condition toward the edge server. In this paper, we leverage reconfigurable intelligent surface (RIS) to mitigate the communication bottleneck of over-the-air FL and explicitly characterize the corresponding convergence upper bound. The convergence analysis illustrates the detrimental impact of the accumulated aggregation error over all rounds and inspires us to formulate a time-average transmission distortion minimization problem by jointly optimizing the transceiver and RIS phase-shifts. To reduce the computation complexity and enhance the model aggregation accuracy, we develop a graph neural network (GNN) based learning algorithm to directly map channel coefficients to the optimized network parameters. By exploiting permutation equivalence and invariance properties of graphs, the parameter dimension of the proposed algorithm is independent of the number of edge devices, which reduces the computational complexity and improves the algorithmic scalability. Simulations show that the proposed algorithm speeds up the computation by three orders of magnitude compared to the baselines, while achieving performance superiority and algorithmic robustness.

In this paper, we consider communication-efficient over-the-air federated learning (FL), where multiple edge devices with non-independent and identically distributed datasets perform multiple local iterations in each communication round and then concurrently transmit their updated gradients to an edge server over the same radio channel for global model aggregation using over-the-air computation (AirComp). We derive the upper bound of the time-average norm of the gradients to characterize the convergence of AirComp-assisted FL, which reveals the impact of the model aggregation errors accumulated over all communication rounds on convergence. Based on the convergence analysis, we formulate an optimization problem to minimize the upper bound to enhance the learning performance, followed by proposing an alternating optimization algorithm to facilitate the transceiver design for AirComp-assisted FL. As the alternating optimization algorithm suffers from high computation complexity, we further develop a knowledge-guided learning algorithm that exploits the structure of the analytic expression of the transmit power to achieve computation-efficient transceiver design. Simulation results demonstrate that the proposed knowledge-guided learning algorithm achieves a comparable performance as the alternating optimization algorithm, but with a much lower computation complexity. Moreover, both proposed algorithms outperform the baseline methods in terms of convergence speed and test accuracy.

Joint activity detection and channel estimation (JADCE) for grant-free random access is a critical issue that needs to be addressed to support massive connectivity in IoT networks. However, the existing model-free learning method can only achieve either activity detection or channel estimation, but not both. In this paper, we propose a novel model-free learning method based on generative adversarial network (GAN) to tackle the JADCE problem. We adopt the U-net architecture to build the generator rather than the standard GAN architecture, where a pre-estimated value that contains the activity information is adopted as input to the generator. By leveraging the properties of the pseudoinverse, the generator is refined by using an affine projection and a skip connection to ensure the output of the generator is consistent with the measurement. Moreover, we build a two-layer fully-connected neural network to design pilot matrix for reducing the impact of receiver noise. Simulation results show that the proposed method out-performs the existing methods in high SNR regimes, as both data consistency projection and pilot matrix optimization improve the learning ability.

Grant-free random access has the potential to sup-port massive connectivity in Internet of Things (IoT) networks, where joint activity detection and channel estimation (JADCE) is a key issue that needs to be tackled. The existing methods for JADCE usually suffer from one of the following limitations: high computational complexity, ineffective in inducing sparsity, and incapable of handling complex matrix estimation. To mitigate all the aforementioned limitations, we in this paper develop an effective unfolding neural network framework built upon the proximal operator method to tackle the JADCE problem in IoT networks, where the base station is equipped with multiple antennas. Specifically, the JADCE problem is formulated as a group-sparse-matrix estimation problem, which is regularized by non-convex minimax concave penalty (MCP). This problem can be iteratively solved by using the proximal operator method, based on which we develop a unfolding neural network structure by parameterizing the algorithmic iterations. By further exploiting the coupling structure among the training parameters as well as the analytical computation, we develop two additional unfolding structures to reduce the training complexity. We prove that the proposed algorithm achieves a linear convergence rate. Results show that our proposed three unfolding structures not only achieve a faster convergence rate but also obtain a higher estimation accuracy than the baseline methods.