面向复值信号处理的全息Transformer:将相位干涉融入自注意力机制
Holographic Transformers for Complex-Valued Signal Processing: Integrating Phase Interference into Self-Attention
AI总结:
针对现有深度模型处理复值信号时忽略相位干涉的问题,提出融入波干涉原理的全息Transformer,通过全息注意力与双头解码器保障相位一致性,在多项复值信号任务中取得性能提升,为相干信号建模提供统一物理框架。
摘要:
复值信号同时编码幅度和相位,但大多数深度模型将注意力视为实值相关性,忽略了干涉效应。我们提出Holographic Transformer(全息Transformer),这是一种受物理学启发的架构,将波干涉原理融入自注意力机制。全息注意力通过相对相位调制交互,并对值进行相干叠加,确保幅度与相位的一致性。双头解码器同时重建输入并预测任务输出,避免当损失优先考虑幅度而非相位时出现相位崩溃。我们证明全息注意力实现了离散干涉算子,且在线性混合下能保持相位一致性。在PolSAR图像分类和无线信道预测任务上的实验表现优异,实现了高分类准确率与F1分数、低回归误差,且对相位扰动的鲁棒性有所提升。这些结果表明,在注意力中施加物理一致性可在复值学习中带来可泛化的性能提升,并为相干信号建模提供了一个基于物理学的统一框架。代码可在https://github.com/EonHao/Holographic-Transformers获取。
英文摘要:
Complex-valued signals encode both amplitude and phase, yet most deep models treat attention as real-valued correlation, overlooking interference effects. We introduce the Holographic Transformer, a physics-inspired architecture that incorporates wave interference principles into self-attention. Holographic attention modulates interactions by relative phase and coherently superimposes values, ensuring consistency between amplitude and phase. A dual-headed decoder simultaneously reconstructs the input and predicts task outputs, preventing phase collapse when losses prioritize magnitude over phase. We demonstrate that holographic attention implements a discrete interference operator and maintains phase consistency under linear mixing. Experiments on PolSAR image classification and wireless channel prediction show strong performance, achieving high classification accuracy and F1 scores, low regression error, and increased robustness to phase perturbations. These results highlight that enforcing physical consistency in attention leads to generalizable improvements in complex-valued learning and provides a unified, physics-based framework for coherent signal modeling. The code is available at https://github.com/EonHao/Holographic-Transformers.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。