Learning Locally Interacting Discrete Dynamical Systems: Towards Data-Efficient and Scalable Prediction
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914814133010432 |
|---|---|
| author | Kang, Beomseok Kumar, Harshit Lee, Minah Chakraborty, Biswadeep Mukhopadhyay, Saibal |
| author_facet | Kang, Beomseok Kumar, Harshit Lee, Minah Chakraborty, Biswadeep Mukhopadhyay, Saibal |
| contents | Locally interacting dynamical systems, such as epidemic spread, rumor propagation through crowd, and forest fire, exhibit complex global dynamics originated from local, relatively simple, and often stochastic interactions between dynamic elements. Their temporal evolution is often driven by transitions between a finite number of discrete states. Despite significant advancements in predictive modeling through deep learning, such interactions among many elements have rarely explored as a specific domain for predictive modeling. We present Attentive Recurrent Neural Cellular Automata (AR-NCA), to effectively discover unknown local state transition rules by associating the temporal information between neighboring cells in a permutation-invariant manner. AR-NCA exhibits the superior generalizability across various system configurations (i.e., spatial distribution of states), data efficiency and robustness in extremely data-limited scenarios even in the presence of stochastic interactions, and scalability through spatial dimension-independent prediction. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_06460 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Learning Locally Interacting Discrete Dynamical Systems: Towards Data-Efficient and Scalable Prediction Kang, Beomseok Kumar, Harshit Lee, Minah Chakraborty, Biswadeep Mukhopadhyay, Saibal Systems and Control Machine Learning Locally interacting dynamical systems, such as epidemic spread, rumor propagation through crowd, and forest fire, exhibit complex global dynamics originated from local, relatively simple, and often stochastic interactions between dynamic elements. Their temporal evolution is often driven by transitions between a finite number of discrete states. Despite significant advancements in predictive modeling through deep learning, such interactions among many elements have rarely explored as a specific domain for predictive modeling. We present Attentive Recurrent Neural Cellular Automata (AR-NCA), to effectively discover unknown local state transition rules by associating the temporal information between neighboring cells in a permutation-invariant manner. AR-NCA exhibits the superior generalizability across various system configurations (i.e., spatial distribution of states), data efficiency and robustness in extremely data-limited scenarios even in the presence of stochastic interactions, and scalability through spatial dimension-independent prediction. |
| title | Learning Locally Interacting Discrete Dynamical Systems: Towards Data-Efficient and Scalable Prediction |
| topic | Systems and Control Machine Learning |
| url | https://arxiv.org/abs/2404.06460 |