Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2510.05385 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912632497242112 |
|---|---|
| author | Arni, Rohan Blanco, Carlos |
| author_facet | Arni, Rohan Blanco, Carlos |
| contents | Physics-Informed Neural Networks (PINNs) are a useful framework for approximating partial differential equation solutions using deep learning methods. In this paper, we propose a principled redesign of the PINNsformer, a Transformer-based PINN architecture. We present the Spectral PINNSformer (S-Pformer), a refinement of encoder-decoder PINNSformers that addresses two key issues; 1. the redundancy (i.e. increased parameter count) of the encoder, and 2. the mitigation of spectral bias. We find that the encoder is unnecessary for capturing spatiotemporal correlations when relying solely on self-attention, thereby reducing parameter count. Further, we integrate Fourier feature embeddings to explicitly mitigate spectral bias, enabling adaptive encoding of multiscale behaviors in the frequency domain. Our model outperforms encoder-decoder PINNSformer architectures across all benchmarks, achieving or outperforming MLP performance while reducing parameter count significantly. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_05385 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Physics-Informed Neural Networks with Fourier Features and Attention-Driven Decoding Arni, Rohan Blanco, Carlos Machine Learning Computational Physics Physics-Informed Neural Networks (PINNs) are a useful framework for approximating partial differential equation solutions using deep learning methods. In this paper, we propose a principled redesign of the PINNsformer, a Transformer-based PINN architecture. We present the Spectral PINNSformer (S-Pformer), a refinement of encoder-decoder PINNSformers that addresses two key issues; 1. the redundancy (i.e. increased parameter count) of the encoder, and 2. the mitigation of spectral bias. We find that the encoder is unnecessary for capturing spatiotemporal correlations when relying solely on self-attention, thereby reducing parameter count. Further, we integrate Fourier feature embeddings to explicitly mitigate spectral bias, enabling adaptive encoding of multiscale behaviors in the frequency domain. Our model outperforms encoder-decoder PINNSformer architectures across all benchmarks, achieving or outperforming MLP performance while reducing parameter count significantly. |
| title | Physics-Informed Neural Networks with Fourier Features and Attention-Driven Decoding |
| topic | Machine Learning Computational Physics |
| url | https://arxiv.org/abs/2510.05385 |