NetDiff用扩散模型生成并快速更新移动网络拓扑，提升全局一致性。
NetDiff: Graph Diffusion with Improved Global Capabilities to Generate and Update Mobile Network Topologies
- 基于节点条件的去噪扩散模型，结合全局注意力机制生成方向性链接。
- 仅用少量迭代即可完成拓扑更新，推理时间恒定且性能超95%目标值。
- 适合高动态移动网络场景，尤其适用于需快速重配置的通信系统。
我们提出NetDiff，一种节点条件的去噪扩散模型，用于生成定向链路拓扑及双向收发时隙分配，适用于移动自组织网络。定向天线虽可实现高吞吐量，但需在扇区、干扰、连通性和半双工约束下做出全局一致的链路决策。NetDiff通过绝对交叉注意力调制（ACAM）令牌提供置换不变的全局信号，帮助模型匹配图级统计量（如密度和扇区使用率）。此外，我们提出部分扩散机制，仅需少量去噪步骤即可对现有拓扑进行更新，支持移动环境下的快速重配置。NetDiff在恒定推理时间内达到超过95%的目标性能，优于启发式与全向基线方法，并在关键指标上超越强基准的扩散图变换器模型。
原文摘要 · Abstract (English)
We introduce NetDiff, a node-conditioned denoising diffusion model that generates directional link topologies and a two-slot transmit/receive parity for mobile ad hoc networks. Directional antennas can yield high throughput but require globally consistent link decisions under sector, interference, connectivity, and half-duplex constraints. NetDiff improves global coherence with Absolute Cross-Attentive Modulation (ACAM) tokens, which provide permutation-invariant global signals and help the model match graph-level counts (e.g., density and sector usage). We also propose partial diffusion to update an existing topology with a small number of denoising steps, enabling fast reconfiguration under mobility. NetDiff reaches over 95 % of target performance with constant inference time, outperforms heuristic and omnidirectional baselines, and improves over a strong diffusion graph-transformer baseline in key metrics.
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。