用物理规律提升无人机通信模型的可解释性与效率
PIKAN: Physics-Inspired Kolmogorov-Arnold Networks for Explainable UAV Channel Modelling
- 将自由空间损耗等物理规律作为灵活先验嵌入网络
- 仅用232个参数达到深度学习模型精度，比MLP轻37倍
- 生成符合传播规律的符号表达式，适合需要可解释性的场景
无人机（UAV）通信需要准确且可解释的空对地（A2G）信道模型，以适应非平稳传播环境。传统确定性模型解释性强但僵化，深度学习模型精度高但缺乏可解释性。为此，本文提出物理启发的柯尔莫戈洛夫-阿诺德网络（PIKAN），将自由空间路径损耗、双射线反射等物理原理作为灵活归纳偏置融入学习过程。不同于物理信息神经网络（PINNs），PIKAN 更灵活地引入物理知识，支持更高效的训练。在实测无人机A2G数据上的实验表明，PIKAN在保持与测量高度相关性的同时，精度媲美深度学习模型，且仅需232个参数，比含数千参数的多层感知机（MLP）基线轻37倍，并生成符合传播定律的符号表达式。该结果凸显了PIKAN在6G及后5G网络中高效、可解释、可扩展的信道建模潜力。
原文摘要 · Abstract (English)
Unmanned aerial vehicle (UAV) communications demand accurate yet interpretable air-to-ground (A2G) channel models that can adapt to nonstationary propagation environments. While deterministic models offer interpretability and deep learning (DL) models provide accuracy, both approaches suffer from either rigidity or a lack of explainability. To bridge this gap, we propose the Physics-Inspired Kolmogorov-Arnold Network (PIKAN) that embeds physical principles (e.g., free-space path loss, two-ray reflections) into the learning process. Unlike physics-informed neural networks (PINNs), PIKAN is more flexible for applying physical information because it introduces them as flexible inductive biases. Thus, it enables a more flexible training process. Experiments on UAV A2G measurement data show that PIKAN achieves comparable accuracy to DL models while providing symbolic and explainable expressions aligned with propagation laws. Remarkably, PIKAN achieves this performance with only 232 parameters, making it up to 37 times lighter than multilayer perceptron (MLP) baselines with thousands of parameters, without sacrificing correlation with measurements and also providing symbolic expressions. These results highlight PIKAN as an efficient, interpretable, and scalable solution for UAV channel modelling in beyond-5G and 6G networks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。