dorsal/arxiv
View SchemaChannel Knowledge Map Construction via Guided Flow Matching
| Authors | Ziyu Huang, Yong Zeng, Shen Fu, Xiaoli Xu, Hongyang Du |
|---|---|
| Categories | |
| ArXiv ID | 2601.06156vv1 |
| URL | https://arxiv.org/abs/2601.06156 |
| License | http://creativecommons.org/licenses/by/4.0/ |
Abstract
The efficient construction of accurate channel knowledge maps (CKMs) is crucial for unleashing the full potential of environment-aware wireless networks, yet it remains a difficult ill-posed problem due to the sparsity of available location-specific channel knowledge data. Although diffusion-based methods such as denoising diffusion probabilistic models (DDPMs) have been exploited for CKM construction, they rely on iterative stochastic sampling, rendering them too slow for real-time wireless applications. To bridge the gap between high fidelity and efficient CKM construction, this letter introduces a novel framework based on linear transport guided flow matching (LT-GFM). Deviating from the noise-removal paradigm of diffusion models, our approach models the CKM generation process as a deterministic ordinary differential equation (ODE) that follows linear optimal transport paths, thereby drastically reducing the number of required inference steps. We propose a unified architecture that is applicable to not only the conventional channel gain map (CGM) construction, but also the more challenging spatial correlation map (SCM) construction. To achieve physics-informed CKM constructions, we integrate environmental semantics (e.g., building masks) for edge recovery and enforce Hermitian symmetry for property of the SCM. Simulation results verify that LT-GFM achieves superior distributional fidelity with significantly lower Fr\'echet Inception Distance (FID) and accelerates inference speed by a factor of 25 compared to DDPMs.
{
"annotation_id": "e323504f-917a-4335-9e60-cb8a13869965",
"date_created": "2026-02-17T05:53:05.008000Z",
"date_modified": "2026-02-17T05:53:05.008000Z",
"file_hash": "412411089bf965880d8be78897f18c951f623e2000b385026e3f367eea48b134",
"private": false,
"record": {
"abstract": "The efficient construction of accurate channel knowledge maps (CKMs) is crucial for unleashing the full potential of environment-aware wireless networks, yet it remains a difficult ill-posed problem due to the sparsity of available location-specific channel knowledge data. Although diffusion-based methods such as denoising diffusion probabilistic models (DDPMs) have been exploited for CKM construction, they rely on iterative stochastic sampling, rendering them too slow for real-time wireless applications. To bridge the gap between high fidelity and efficient CKM construction, this letter introduces a novel framework based on linear transport guided flow matching (LT-GFM). Deviating from the noise-removal paradigm of diffusion models, our approach models the CKM generation process as a deterministic ordinary differential equation (ODE) that follows linear optimal transport paths, thereby drastically reducing the number of required inference steps. We propose a unified architecture that is applicable to not only the conventional channel gain map (CGM) construction, but also the more challenging spatial correlation map (SCM) construction. To achieve physics-informed CKM constructions, we integrate environmental semantics (e.g., building masks) for edge recovery and enforce Hermitian symmetry for property of the SCM. Simulation results verify that LT-GFM achieves superior distributional fidelity with significantly lower Fr\\\u0027echet Inception Distance (FID) and accelerates inference speed by a factor of 25 compared to DDPMs.",
"arxiv_id": "2601.06156",
"authors": [
"Ziyu Huang",
"Yong Zeng",
"Shen Fu",
"Xiaoli Xu",
"Hongyang Du"
],
"categories": [
"cs.IT",
"cs.AI",
"math.IT"
],
"license": "http://creativecommons.org/licenses/by/4.0/",
"title": "Channel Knowledge Map Construction via Guided Flow Matching",
"url": "https://arxiv.org/abs/2601.06156",
"version": "v1"
},
"schema_id": "dorsal/arxiv",
"source": {
"execution_id": "0a834bd6-9379-4261-b455-e62fdb9bcdc8",
"id": "arXiv Dataset",
"type": "Model",
"variant": "snapshot-2026-01-17",
"version": "0.1.0"
},
"user_id": 1000002
}