In this paper, we intent to handle this emerging issue.

Scaling law that rewards large datasets, complex models and enhanced data granularity has been observed in various fields of deep learning.

Inthis paper, we present GRAPHSPLINENETS, a novel deep-learning method to speed up the forecasting of physical systems by reducing the grid size and number of iteration steps of deep surrogate models. Our method uses two differentiable orthogonal spline collocation methods to efficiently predict response at any location in time and space. Additionally, we introduce an adaptive collocation strategy in space to prioritize sampling from the most important regions.

Current methods for identifying adversarial prompts aimed at "attacking" LLMs and eliciting undesirable outputs are limited by several factors.

Correlation mechanism to capture cross-time dependency for forecasting. Besides, the dimension of the channel is set to 16 based on efficiency considerations. Weather, and the look-back window size is set as 96. Proposition 2. The time and space complexity for the Cross-variable GNN is Frequency enhanced decomposed transformer for long-term series forecasting.

To address the above issues, we propose CrossGNN, a linear complexity GNN model to refine the cross-scale and cross-variable interaction for MTS. To deal with the unexpected noise in time dimension, an adaptive multi-scale identifier (AMSI) is leveraged to construct multi-scale time series with reduced noise.

Dynamics forecasting refers to the task of predicting the future behavior of a dynamic system, involving learning the underlying dynamics governing the system's evolution to make accurate predictions