mlsanityData to 14 Oct 2026

NetDiff: Graph Diffusion with Improved Global Capabilities to Generate and Update Mobile Network Topologies

arXiv 2410.08238 ↗First posted 9 Oct 2024cs.SI cs.LG cs.NIcited by 2

On the map: Diffusion models → Diffusion for compression and wireless

Abstract (arXiv)

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.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Diffusion for compression and wireless, one of 14 directions in Diffusion models. Builds on 25 of its 41 references that are in the map. First posted on arXiv 9 Oct 2024.

Builds on

25 of 41 references.

References · 25

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  3. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  4. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,333
  5. 2016Variational Graph Auto-Encoderscited by 1,382
  6. 2022Equivariant Diffusion for Molecule Generation in 3Dcited by 677
  7. 2018GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Modelscited by 413
  8. 2018MolGAN: An implicit generative model for small molecular graphscited by 393
  9. 2019Provably Powerful Graph Networkscited by 389
  10. 2018GraphVAE: Towards Generation of Small Graphs Using Variational Autoencoderscited by 383
  11. 2020GraphAF: a Flow-based Autoregressive Model for Molecular Graph Generationcited by 305
  12. 2020Reinforcement Learning for Combinatorial Optimization: A Surveycited by 236
13 more
  1. 2023DIFUSCO: Graph-based Diffusion Solvers for Combinatorial Optimizationcited by 221
  2. 2017GraphGAN: Graph Representation Learning with Generative Adversarial Netscited by 121
  3. 2022SPECTRE: Spectral Conditioning Helps to Overcome the Expressivity Limits of One-shot Graph Generatorscited by 99
  4. 2023MiDi: Mixed Graph and 3D Denoising Diffusion for Molecule Generationcited by 98
  5. 2019GNN-FiLM: Graph Neural Networks with Feature-wise Linear Modulationcited by 75
  6. 2020Pointer Graph Networkscited by 53
  7. 2019RouteNet: Leveraging Graph Neural Networks for network modeling and optimization in SDNcited by 47
  8. 2019GCN-GAN: A Non-linear Temporal Link Prediction Model for Weighted Dynamic Networkscited by 40
  9. 2022RouteNet-Fermi: Network Modeling with Graph Neural Networkscited by 17
  10. 2024Graph Reinforcement Learning for Combinatorial Optimization: A Survey and Unifying Perspectivecited by 16
  11. 2021Visualizing hierarchies in scRNA-seq data using a density tree-biased autoencodercited by 2
  12. 2024Empowering Wireless Networks with Artificial Intelligence Generated Graphcited by 2
  13. 2017NeuRoute: Predictive Dynamic Routing for Software-Defined Networkscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Graph Convolutional Attention: A Spectral Perspective on Graph Denoising and Diffusioncited by 0
  2. 2026Escaping Oversquashing: Addressable and Support-Aware Global Memory for Message Passing Networkscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026GD4: Graph-based Discrete Denoising Diffusion for MIMO Detection
  2. 2026RMPrior: Bridging Propagation Priors and Diffusion Refinement for Efficient Radio Map Construction
  3. 2026Graph Residual Conjugate Diffusion: SNR-Equalized Heat Flow for Graph Signals
  4. 2026RadioDiff-Flux: Efficient Radio Map Construction via Generative Denoise Diffusion Model Trajectory Midpoint Reuse
  5. 2025Diffusion Models for Future Networks and Communications: A Comprehensive Survey
  6. 2026RadioDiff-FS: Physics-Informed Manifold Alignment in Few-Shot Diffusion Models for High-Fidelity Radio Map Construction
  7. 2025Graph-Aware Diffusion for Signal Generation
  8. 2025Denoising Refinement Diffusion Models for Simultaneous Generation of Multi-scale Mobile Network Traffic