Modeling Spatio-temporal Dynamical Systems with Neural Discrete Learning and Levels-of-Experts
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909099273224192 |
|---|---|
| author | Wang, Kun Wu, Hao Zhang, Guibin Fang, Junfeng Liang, Yuxuan Wu, Yuankai Zimmermann, Roger Wang, Yang |
| author_facet | Wang, Kun Wu, Hao Zhang, Guibin Fang, Junfeng Liang, Yuxuan Wu, Yuankai Zimmermann, Roger Wang, Yang |
| contents | In this paper, we address the issue of modeling and estimating changes in the state of the spatio-temporal dynamical systems based on a sequence of observations like video frames. Traditional numerical simulation systems depend largely on the initial settings and correctness of the constructed partial differential equations (PDEs). Despite recent efforts yielding significant success in discovering data-driven PDEs with neural networks, the limitations posed by singular scenarios and the absence of local insights prevent them from performing effectively in a broader real-world context. To this end, this paper propose the universal expert module -- that is, optical flow estimation component, to capture the evolution laws of general physical processes in a data-driven fashion. To enhance local insight, we painstakingly design a finer-grained physical pipeline, since local characteristics may be influenced by various internal contextual information, which may contradict the macroscopic properties of the whole system. Further, we harness currently popular neural discrete learning to unveil the underlying important features in its latent space, this process better injects interpretability, which can help us obtain a powerful prior over these discrete random variables. We conduct extensive experiments and ablations to demonstrate that the proposed framework achieves large performance margins, compared with the existing SOTA baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_05970 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Modeling Spatio-temporal Dynamical Systems with Neural Discrete Learning and Levels-of-Experts Wang, Kun Wu, Hao Zhang, Guibin Fang, Junfeng Liang, Yuxuan Wu, Yuankai Zimmermann, Roger Wang, Yang Machine Learning Artificial Intelligence In this paper, we address the issue of modeling and estimating changes in the state of the spatio-temporal dynamical systems based on a sequence of observations like video frames. Traditional numerical simulation systems depend largely on the initial settings and correctness of the constructed partial differential equations (PDEs). Despite recent efforts yielding significant success in discovering data-driven PDEs with neural networks, the limitations posed by singular scenarios and the absence of local insights prevent them from performing effectively in a broader real-world context. To this end, this paper propose the universal expert module -- that is, optical flow estimation component, to capture the evolution laws of general physical processes in a data-driven fashion. To enhance local insight, we painstakingly design a finer-grained physical pipeline, since local characteristics may be influenced by various internal contextual information, which may contradict the macroscopic properties of the whole system. Further, we harness currently popular neural discrete learning to unveil the underlying important features in its latent space, this process better injects interpretability, which can help us obtain a powerful prior over these discrete random variables. We conduct extensive experiments and ablations to demonstrate that the proposed framework achieves large performance margins, compared with the existing SOTA baselines. |
| title | Modeling Spatio-temporal Dynamical Systems with Neural Discrete Learning and Levels-of-Experts |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2402.05970 |