# PhyG-MoE: A Physics-Guided Mixture-of-Experts Framework for Energy-Efficient GNSS Interference Recognition

arXiv: https://arxiv.org/abs/2601.12798 · HTML: https://mlsanity.com/paper/2601.12798/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in MoE theory and gating functions, one of 12 directions in Mixture-of-experts.
- Builds on 21 of its 65 references that are in the map.
- First posted on arXiv 19 Jan 2026.

## Placed in

- Mixture-of-experts / [MoE theory and gating functions](https://mlsanity.com/moe/moe-theory-and-gating-functions/)

## Builds on (most cited first, 21 of 21)

- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding](https://mlsanity.com/paper/2006.16668/) (2020)
- [Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet](https://mlsanity.com/paper/2101.11986/) (2021)
- [ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders](https://mlsanity.com/paper/2301.00808/) (2023)
- [GhostNet: More Features from Cheap Operations](https://mlsanity.com/paper/1911.11907/) (2019)
- [Selective Kernel Networks](https://mlsanity.com/paper/1903.06586/) (2019)
- [A Vision of 6G Wireless Systems: Applications, Trends, Technologies, and Open Research Problems](https://mlsanity.com/paper/1902.10265/) (2019)
- [MobileNetV4 -- Universal Models for the Mobile Ecosystem](https://mlsanity.com/paper/2404.10518/) (2024)
- [Large Selective Kernel Network for Remote Sensing Object Detection](https://mlsanity.com/paper/2303.09030/) (2023)
- [TransNeXt: Robust Foveal Visual Perception for Vision Transformers](https://mlsanity.com/paper/2311.17132/) (2023)
- [6G Internet of Things: A Comprehensive Survey](https://mlsanity.com/paper/2108.04973/) (2021)
- [Generative AI-driven Semantic Communication Networks: Architecture, Technologies and Applications](https://mlsanity.com/paper/2401.00124/) (2023)
- [Optimizing Space-Air-Ground Integrated Networks by Artificial Intelligence](https://mlsanity.com/paper/1808.01053/) (2018)
- [GNSS Signal Authentication via Power and Distortion Monitoring](https://mlsanity.com/paper/1702.06554/) (2017)
- [Robust Beamforming Design for Near-Field DMA-NOMA mmWave Communications With Imperfect Position Information](https://mlsanity.com/paper/2409.15894/) (2024)
- [Movable Antenna-Aided Cooperative ISAC Network with Time Synchronization error and Imperfect CSI](https://mlsanity.com/paper/2501.15410/) (2025)
- [Flexible WMMSE Beamforming for MU-MIMO Movable Antenna Communications](https://mlsanity.com/paper/2503.17718/) (2025)
- [Distortion-Aware Hybrid Beamforming for Integrated Sensing and Communication](https://mlsanity.com/paper/2507.14018/) (2025)
- [Robust Optimization for Movable Antenna-aided Cell-Free ISAC with Time Synchronization Errors](https://mlsanity.com/paper/2508.13818/) (2025)
- [Crosstalk-Resilient Beamforming for Movable Antenna Enabled Integrated Sensing and Communication](https://mlsanity.com/paper/2509.03273/) (2025)
- [Cluster-Based Multi-Agent Task Scheduling for Space-Air-Ground Integrated Networks](https://mlsanity.com/paper/2412.10700/) (2024)

## Built on by (most cited first, 4 of 4)

- [Sparse Gain Radio Map Reconstruction With Geometry Priors and Uncertainty-Guided Measurement Selection](https://mlsanity.com/paper/2604.05788/) (2026)
- [Geometry-Aware Cross-Height Channel Knowledge Map Prediction for UAV-Assisted Communications With Uncertainty-Guided 3D Sensing](https://mlsanity.com/paper/2607.00887/) (2026)
- [QuaMoE-DRF: Proactive Beam and Rate Adaptation via Multimodal Dynamic Radio Map Forecasting in ISAC Networks](https://mlsanity.com/paper/2607.00974/) (2026)
- [SPOC-Net: Single-Primitive Online Composition Network for GNSS Jamming Set Recognition](https://mlsanity.com/paper/2609.34875/) (2026)

## Abstract (arXiv)

Complex electromagnetic interference increasingly compromises Global Navigation Satellite Systems (GNSS), threatening the reliability of Space-Air-Ground Integrated Networks (SAGIN). Although deep learning has advanced interference recognition, current static models suffer from a fundamental limitation: they impose a fixed computational topology regardless of the input's physical entropy. This rigidity leads to severe resource mismatch, where simple primitives consume the same processing cost as chaotic, saturated mixtures. To resolve this, this paper introduces PhyG-MoE (Physics-Guided Mixture-of-Experts), a framework designed to dynamically align model capacity with signal complexity. Unlike static architectures, the proposed system employs a spectrum-based gating mechanism that routes signals based on their spectral feature entanglement. A high-capacity TransNeXt expert is activated on-demand to disentangle complex features in saturated scenarios, while lightweight experts handle fundamental signals to minimize latency. Evaluations on 21 jamming categories demonstrate that PhyG-MoE achieves an overall accuracy of 97.58%. By resolving the intrinsic conflict between static computing and dynamic electromagnetic environments, the proposed framework significantly reduces computational overhead without performance degradation, offering a viable solution for resource-constrained cognitive receivers.