M3Net: A Multi-Metric Mixture of Experts Network Digital Twin with Graph Neural Networks

• URL: http://arxiv.org/abs/2512.09797v1
• Date: Wed, 10 Dec 2025 16:12:42 GMT
• Title: M3Net: A Multi-Metric Mixture of Experts Network Digital Twin with Graph Neural Networks
• Authors: Blessed Guda, Carlee Joe-Wong,
• Abstract summary: We introduce M3Net, a graph neural network architecture to estimate multiple performance metrics from an expanded set of network state data.<n>M3Net significantly enhances the accuracy of flow delay predictions by reducing the MAPE (Mean Absolute Percentage Error) from 20.06% to 17.39%.
• Score: 18.215893951726166
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The rise of 5G/6G network technologies promises to enable applications like autonomous vehicles and virtual reality, resulting in a significant increase in connected devices and necessarily complicating network management. Even worse, these applications often have strict, yet heterogeneous, performance requirements across metrics like latency and reliability. Much recent work has thus focused on developing the ability to predict network performance. However, traditional methods for network modeling, like discrete event simulators and emulation, often fail to balance accuracy and scalability. Network Digital Twins (NDTs), augmented by machine learning, present a viable solution by creating virtual replicas of physical networks for real- time simulation and analysis. State-of-the-art models, however, fall short of full-fledged NDTs, as they often focus only on a single performance metric or simulated network data. We introduce M3Net, a Multi-Metric Mixture-of-experts (MoE) NDT that uses a graph neural network architecture to estimate multiple performance metrics from an expanded set of network state data in a range of scenarios. We show that M3Net significantly enhances the accuracy of flow delay predictions by reducing the MAPE (Mean Absolute Percentage Error) from 20.06% to 17.39%, while also achieving 66.47% and 78.7% accuracy on jitter and packets dropped for each flow

Related papers

• RouteNet-Gauss: Hardware-Enhanced Network Modeling with Machine Learning [3.6613770745846796]
  This paper introduces RouteNet-Gauss, a novel integration of a testbed network with a Machine Learning (ML) model to address these challenges.<n>By using the testbed as a hardware accelerator, RouteNet-Gauss generates training datasets rapidly and simulates network scenarios with high fidelity to real-world conditions.<n> Experimental results show that RouteNet-Gauss significantly reduces prediction errors by up to 95% and achieves a 488x speedup in inference time compared to state-of-the-art DES-based methods.
  arXiv  Detail & Related papers  (2025-01-15T15:00:11Z)
• A Multi-Fidelity Graph U-Net Model for Accelerated Physics Simulations [1.2430809884830318]
  We propose a novel GNN architecture, Multi-Fidelity U-Net, that utilizes the advantages of the multi-fidelity methods for enhancing the performance of the GNN model.<n>We show that the proposed approach performs significantly better in accuracy and data requirement.<n>We also present Multi-Fidelity U-Net Lite, a faster version of the proposed architecture, with 35% faster training, with 2 to 5% reduction in accuracy.
  arXiv  Detail & Related papers  (2024-12-19T20:09:38Z)
• Latency-aware Unified Dynamic Networks for Efficient Image Recognition [72.8951331472913]
  LAUDNet is a framework to bridge the theoretical and practical efficiency gap in dynamic networks. It integrates three primary dynamic paradigms-spatially adaptive computation, dynamic layer skipping, and dynamic channel skipping. It can notably reduce the latency of models like ResNet by over 50% on platforms such as V100,3090, and TX2 GPUs.
  arXiv  Detail & Related papers  (2023-08-30T10:57:41Z)
• EasyNet: An Easy Network for 3D Industrial Anomaly Detection [49.26348455493123]
  3D anomaly detection is an emerging and vital computer vision task in industrial manufacturing. We propose an easy and deployment-friendly network (called EasyNet) without using pre-trained models and memory banks. Experiments show that EasyNet achieves an anomaly detection AUROC of 92.6% without using pre-trained models and memory banks.
  arXiv  Detail & Related papers  (2023-07-26T02:46:50Z)
• RouteNet-Fermi: Network Modeling with Graph Neural Networks [7.227467283378366]
  We present RouteNet-Fermi, a custom Graph Neural Networks (GNN) model that shares the same goals as Queuing Theory. The proposed model predicts accurately the delay, jitter, and packet loss of a network. Our experimental results show that RouteNet-Fermi achieves similar accuracy as computationally-expensive packet-level simulators.
  arXiv  Detail & Related papers  (2022-12-22T23:02:40Z)
• FPGA-optimized Hardware acceleration for Spiking Neural Networks [69.49429223251178]
  This work presents the development of a hardware accelerator for an SNN, with off-line training, applied to an image recognition task. The design targets a Xilinx Artix-7 FPGA, using in total around the 40% of the available hardware resources. It reduces the classification time by three orders of magnitude, with a small 4.5% impact on the accuracy, if compared to its software, full precision counterpart.
  arXiv  Detail & Related papers  (2022-01-18T13:59:22Z)
• FADNet++: Real-Time and Accurate Disparity Estimation with Configurable Networks [19.29846600092521]
  FADNet++ is an efficient deep network for disparity estimation. It can boost its accuracy with a fast model inference speed for real-time applications. It achieves a new state-of-the-art result for the SceneFlow dataset.
  arXiv  Detail & Related papers  (2021-10-06T08:50:33Z)
• DS-Net++: Dynamic Weight Slicing for Efficient Inference in CNNs and Transformers [105.74546828182834]
  We show a hardware-efficient dynamic inference regime, named dynamic weight slicing, which adaptively slice a part of network parameters for inputs with diverse difficulty levels. We present dynamic slimmable network (DS-Net) and dynamic slice-able network (DS-Net++) by input-dependently adjusting filter numbers of CNNs and multiple dimensions in both CNNs and transformers.
  arXiv  Detail & Related papers  (2021-09-21T09:57:21Z)
• Multi-Exit Semantic Segmentation Networks [78.44441236864057]
  We propose a framework for converting state-of-the-art segmentation models to MESS networks. specially trained CNNs that employ parametrised early exits along their depth to save during inference on easier samples. We co-optimise the number, placement and architecture of the attached segmentation heads, along with the exit policy, to adapt to the device capabilities and application-specific requirements.
  arXiv  Detail & Related papers  (2021-06-07T11:37:03Z)
• ANNETTE: Accurate Neural Network Execution Time Estimation with Stacked Models [56.21470608621633]
  We propose a time estimation framework to decouple the architectural search from the target hardware. The proposed methodology extracts a set of models from micro- kernel and multi-layer benchmarks and generates a stacked model for mapping and network execution time estimation. We compare estimation accuracy and fidelity of the generated mixed models, statistical models with the roofline model, and a refined roofline model for evaluation.
  arXiv  Detail & Related papers  (2021-05-07T11:39:05Z)
• FADNet: A Fast and Accurate Network for Disparity Estimation [18.05392578461659]
  We propose an efficient and accurate deep network for disparity estimation named FADNet. It exploits efficient 2D based correlation layers with stacked blocks to preserve fast computation. It contains multi-scale predictions so as to exploit a multi-scale weight scheduling training technique to improve the accuracy.
  arXiv  Detail & Related papers  (2020-03-24T10:27:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.