LGFNet: Local-Global Fusion Network with Fidelity Gap Delta Learning for Multi-Source Aerodynamics

• URL: http://arxiv.org/abs/2603.29303v1
• Date: Tue, 31 Mar 2026 06:13:20 GMT
• Title: LGFNet: Local-Global Fusion Network with Fidelity Gap Delta Learning for Multi-Source Aerodynamics
• Abstract summary: Local-Global Fusion Network (LGFNet) for multi-scale feature decomposition.<n>Experiments demonstrate that LGFNet achieves state-of-the-art (SOTA) performance in both accuracy and uncertainty reduction across diverse aerodynamic scenarios.
• Score: 8.176798147806648
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The precise fusion of computational fluid dynamic (CFD) data, wind tunnel tests data, and flight tests data in aerodynamic area is essential for obtaining comprehensive knowledge of both localized flow structures and global aerodynamic trends across the entire flight envelope. However, existing methodologies often struggle to balance high-resolution local fidelity with wide-range global dependency, leading to either a loss of sharp discontinuities or an inability to capture long-range topological correlations. We propose Local-Global Fusion Network (LGFNet) for multi-scale feature decomposition to extract this dual-natured aerodynamic knowledge. To this end, LGFNet combines a spatial perception layer that integrates a sliding window mechanism with a relational reasoning layer based on self-attention, simultaneously reinforcing the continuity of fine-grained local features (e.g., shock waves) and capturing long-range flow information. Furthermore, the fidelity gap delta learning (FGDL) strategy is proposed to treat CFD data as a "low-frequency carrier" to explicitly approximate nonlinear discrepancies. This approach prevents unphysical smoothing while inheriting the foundational physical trends from the simulation baseline. Experiments demonstrate that LGFNet achieves state-of-the-art (SOTA) performance in both accuracy and uncertainty reduction across diverse aerodynamic scenarios.

Related papers

• DSFNet: Learning Dual-Domain Spectral Operators for Multi-Modality Spatio-Temporal Forecasting in Urban Transportation Systems [51.72074484150301]
  We propose the Dual-Domain Spectral Network (DSFNet) to explicitly model the relationships between variables.<n>Our framework employs dual-domain spectral filtering to capture heterogeneous spatial patterns.<n>Compared with the second-best baselines, DSFNet reduces MAE by 3.21%-10.16% across these datasets.
  arXiv  Detail & Related papers  (2026-06-05T07:33:57Z)
• Multiscale Physics-Informed Neural Network for Complex Fluid Flows with Long-Range Dependencies [7.8263969790121815]
  Domain-Decomposed and Shifted Physics-Informed Neural Network (DDS-PINN)<n>For turbulent Residual flow at Re = 10,000, the sparse framework achieves convergence to O(10-4) using only 500 random supervision points ( 0.3 % of the total domain)<n>This approach demonstrates strong potential for the super-resolution of complex turbulent flows from measurements.
  arXiv  Detail & Related papers  (2026-04-07T09:54:50Z)
• Adaptive Dual-Weighting Framework for Federated Learning via Out-of-Distribution Detection [53.45696787935487]
  Federated Learning (FL) enables collaborative model training across large-scale distributed service nodes.<n>In real-world service-oriented deployments, data generated by heterogeneous users, devices, and application scenarios are inherently non-IID.<n>We propose FLood, a novel FL framework inspired by out-of-distribution (OOD) detection.
  arXiv  Detail & Related papers  (2026-02-01T05:54:59Z)
• Breaking the Regional Barrier: Inductive Semantic Topology Learning for Worldwide Air Quality Forecasting [99.4484686548807]
  We propose OmniAir, a semantic topology learning framework tailored for global station-level prediction.<n>Our approach effectively captures long-range non-Euclidean correlations and physical diffusion patterns across unevenly distributed global networks.<n>Experiments show that OmniAir achieves state-of-the-art performance against 18 baselines, maintaining high efficiency and scalability with speeds nearly 10 times faster than existing models.
  arXiv  Detail & Related papers  (2026-01-29T15:58:07Z)
• Widening the Network Mitigates the Impact of Data Heterogeneity on FedAvg [6.185573921868495]
  Federated learning (FL) enables decentralized clients to train a model collaboratively without sharing local data.<n>We prove that the impact of data heterogeneity diminishes as the width of neural networks increases, ultimately vanishing when the width approaches infinity.<n>In the infinite-width regime, we further prove that both the global and local models in FedAvg behave as linear models, and that FedAvg achieves the same generalization performance as centralized learning with the same number of GD iterations.
  arXiv  Detail & Related papers  (2025-08-18T02:22:55Z)
• GFocal: A Global-Focal Neural Operator for Solving PDEs on Arbitrary Geometries [5.323843026995587]
  Transformer-based neural operators have emerged as promising surrogate solvers for partial differential equations.<n>We propose GFocal, a method that enforces simultaneous global and local feature learning and fusion.<n>Experiments show that GFocal achieves state-of-the-art performance with an average 15.2% relative gain in five out of six benchmarks.
  arXiv  Detail & Related papers  (2025-08-06T14:02:39Z)
• Optimal Transceiver Design in Over-the-Air Federated Distillation [34.09979141255862]
  We study the transceiver design in terms of the learning convergence rate and the power constraints.<n>We propose a novel approach to find the optimal receiver beam vector for over-the-air aggregation.<n>Results show that the proposed over-the-air approach achieves a significant reduction in communication with only a minor compromise in testing accuracy.
  arXiv  Detail & Related papers  (2025-07-21T05:37:08Z)
• FLEX: A Backbone for Diffusion-Based Modeling of Spatio-temporal Physical Systems [51.15230303652732]
  FLEX (F Low EXpert) is a backbone architecture for generative modeling of-temporal physical systems.<n>It reduces the variance of the velocity field in the diffusion model, which helps stabilize training.<n>It achieves accurate predictions for super-resolution and forecasting tasks using as few features as two reverse diffusion steps.
  arXiv  Detail & Related papers  (2025-05-23T00:07:59Z)
• Stragglers-Aware Low-Latency Synchronous Federated Learning via Layer-Wise Model Updates [71.81037644563217]
  Synchronous federated learning (FL) is a popular paradigm for collaborative edge learning. As some of the devices may have limited computational resources and varying availability, FL latency is highly sensitive to stragglers. We propose straggler-aware layer-wise federated learning (SALF) that leverages the optimization procedure of NNs via backpropagation to update the global model in a layer-wise fashion.
  arXiv  Detail & Related papers  (2024-03-27T09:14:36Z)
• Over-the-Air Federated Learning and Optimization [52.5188988624998]
  We focus on Federated learning (FL) via edge-the-air computation (AirComp) We describe the convergence of AirComp-based FedAvg (AirFedAvg) algorithms under both convex and non- convex settings. For different types of local updates that can be transmitted by edge devices (i.e., model, gradient, model difference), we reveal that transmitting in AirFedAvg may cause an aggregation error. In addition, we consider more practical signal processing schemes to improve the communication efficiency and extend the convergence analysis to different forms of model aggregation error caused by these signal processing schemes.
  arXiv  Detail & Related papers  (2023-10-16T05:49:28Z)
• Fine-tuning Global Model via Data-Free Knowledge Distillation for Non-IID Federated Learning [86.59588262014456]
  Federated Learning (FL) is an emerging distributed learning paradigm under privacy constraint. We propose a data-free knowledge distillation method to fine-tune the global model in the server (FedFTG) Our FedFTG significantly outperforms the state-of-the-art (SOTA) FL algorithms and can serve as a strong plugin for enhancing FedAvg, FedProx, FedDyn, and SCAFFOLD.
  arXiv  Detail & Related papers  (2022-03-17T11:18:17Z)
• Deep Learning Interfacial Momentum Closures in Coarse-Mesh CFD Two-Phase Flow Simulation Using Validation Data [5.099083753474628]
  Feature-similarity measurement (FSM) is developed and applied to improve the simulation capability of two-phase flow with coarse-mesh CFD approach. FSM can substantially improve the prediction of the coarse-mesh CFD model, regardless of the choice of interfacial closures.
  arXiv  Detail & Related papers  (2020-05-07T21:25:22Z)

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.