用相位干扰机制提升神经网络的语义表达与效率
Language as a Wave Phenomenon: Semantic Phase Locking and Interference in Neural Networks
- 引入复数域架构PRISM，通过相位控制实现语义信息分离
- 相位保留时性能稳定，破坏相位则性能严重下降
- 适合关注模型可解释性与高效推理的研究者
在标准Transformer架构中，语义重要性常与激活幅度混淆，掩盖了潜在表示的几何结构。为解耦这些因素，我们提出PRISM，一种复数域架构，旨在分离相位的计算作用。通过施加严格的单位范数约束（|z| = 1），并以门控谐波卷积替代注意力机制，模型被引导在频域利用相位相减干涉来抑制噪声，而非依赖幅度门控。我们进一步构建混合架构——融合相位路由与标准注意力，在评估设置下相比基线展现出更高的参数效率与表示质量。干预性消融实验表明，模型在相位中承载大量任务相关信息：保留相位可维持性能，而破坏相位则导致严重退化。结果共同表明，在所评估规模下，基于相位的谱干涉是一种可用的神经序列建模计算机制。
原文摘要 · Abstract (English)
In standard Transformer architectures, semantic importance is often conflated with activation magnitude, obscuring the geometric structure of latent representations. To disentangle these factors, we introduce PRISM, a complex-valued architecture designed to isolate the computational role of phase. By enforcing a strict unit-norm constraint ($|z| = 1$) and replacing attention with gated harmonic convolutions, the model is encouraged to utilize subtractive interference in the frequency domain to suppress noise, rather than relying on magnitude-based gating. We utilize this constrained regime to study a hybrid architecture -- fusing phase-based routing with standard attention -- which achieves improved parameter efficiency and representation quality compared to baselines in our evaluated settings. Mechanistically, interventional ablations indicate that the model carries substantial task-relevant information in phase: preserving phase largely maintains performance, whereas disrupting phase causes severe degradation. Together, these results suggest that phase-based spectral interference is a usable computational mechanism for neural sequence modeling at the evaluated scale.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。