Continuous-Time Attention: PDE-Guided Mechanisms for Long-Sequence Transformers
About
We propose a novel framework, Continuous_Time Attention, which infuses partial differential equations (PDEs) into the Transformer's attention mechanism to address the challenges of extremely long input sequences. Instead of relying solely on a static attention matrix, we allow attention weights to evolve over a pseudo_time dimension via diffusion, wave, or reaction_diffusion dynamics. This mechanism systematically smooths local noise, enhances long_range dependencies, and stabilizes gradient flow. Theoretically, our analysis shows that PDE_based attention leads to better optimization landscapes and polynomial rather than exponential decay of distant interactions. Empirically, we benchmark our method on diverse experiments_demonstrating consistent gains over both standard and specialized long sequence Transformer variants. Our findings highlight the potential of PDE_based formulations to enrich attention mechanisms with continuous_time dynamics and global coherence.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Irregular Time Series Classification | E-MNIST | Accuracy95.95 | 53 | |
| Irregular Time-series Modeling | spiral | MAE0.3138 | 30 |