Scholarlink

Urban traffic prediction is hindered by heterogeneous sensor configurations and complex wave-like traffic flow dynamics (e.g., congestion waves, stop-and-go oscillations) that conventional neural networks struggle to model effectively. We propose WaveFSL, a novel wave physics-inspired few-shot learning framework that unifies wave interference theory with adaptive neural modules to address these challenges. WaveFSL integrates five key components: (1) a Dynamic Input Projection (DIP) for handling variable-dimensional input through learnable dimension-aware projection; (2) a Traffic Wave Generator (TWG) synthesising parameterised wave components (with amplitude, effective frequency, and phase); (3) a Wave-Constrained Interference (WCI) explicitly modelling congestion propagation via coupled wave superposition; (4) a Wave-Aware Spectral Attention (WASA) for multiscale spectral analysis through resonance scoring and frequency-band decomposition; and (5) a Few-Shot Adaptation with optimal kernels (FSAK) enabling rapid domain adaption and transfer via prototype-based conditioning. By unifying wave interference theory with adaptive neural learning, WaveFSL achieves state-of-the-art performance across four real-world datasets, outperforms baselines (3.2–8.5% MAE reduction), generalises with only 5–10 labelled samples per city, and requires no retraining. It enables interpretable, deployable traffic forecasting under realistic constraints. Code is available at: https://github.com/afofanah/WaveFSL .

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

WaveFSL: Wave Interference-Based Meta-learning for Few-Shot Cross-Modality Traffic Forecasting

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Abdul Joseph Fofanah,
  • Lian Wen,
  • David Chen,
  • Shaoyang Zhang,
  • Alpha Alimamy Kamara

摘要

Urban traffic prediction is hindered by heterogeneous sensor configurations and complex wave-like traffic flow dynamics (e.g., congestion waves, stop-and-go oscillations) that conventional neural networks struggle to model effectively. We propose WaveFSL, a novel wave physics-inspired few-shot learning framework that unifies wave interference theory with adaptive neural modules to address these challenges. WaveFSL integrates five key components: (1) a Dynamic Input Projection (DIP) for handling variable-dimensional input through learnable dimension-aware projection; (2) a Traffic Wave Generator (TWG) synthesising parameterised wave components (with amplitude, effective frequency, and phase); (3) a Wave-Constrained Interference (WCI) explicitly modelling congestion propagation via coupled wave superposition; (4) a Wave-Aware Spectral Attention (WASA) for multiscale spectral analysis through resonance scoring and frequency-band decomposition; and (5) a Few-Shot Adaptation with optimal kernels (FSAK) enabling rapid domain adaption and transfer via prototype-based conditioning. By unifying wave interference theory with adaptive neural learning, WaveFSL achieves state-of-the-art performance across four real-world datasets, outperforms baselines (3.2–8.5% MAE reduction), generalises with only 5–10 labelled samples per city, and requires no retraining. It enables interpretable, deployable traffic forecasting under realistic constraints. Code is available at: https://github.com/afofanah/WaveFSL .