Holographic Transformers for Complex-Valued Signal Processing: Integrating Phase Interference into Self-Attention
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911240105754624 |
|---|---|
| author | Huang, Enhao Zhang, Zhiyu Xu, Tianxiang Xia, Chunshu Hu, Kaichun Yang, Yuchen Pan, Tongtong Dong, Dong Qin, Zhan |
| author_facet | Huang, Enhao Zhang, Zhiyu Xu, Tianxiang Xia, Chunshu Hu, Kaichun Yang, Yuchen Pan, Tongtong Dong, Dong Qin, Zhan |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_19331 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Holographic Transformers for Complex-Valued Signal Processing: Integrating Phase Interference into Self-Attention Huang, Enhao Zhang, Zhiyu Xu, Tianxiang Xia, Chunshu Hu, Kaichun Yang, Yuchen Pan, Tongtong Dong, Dong Qin, Zhan Signal Processing Artificial Intelligence Machine Learning 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. |
| title | Holographic Transformers for Complex-Valued Signal Processing: Integrating Phase Interference into Self-Attention |
| topic | Signal Processing Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2509.19331 |