LaM-SLidE: Latent Space Modeling of Spatial Dynamical Systems via Linked Entities
This addresses the problem of modeling complex spatial dynamical systems, such as chemical molecules or human behavior, for researchers in machine learning and applied sciences, representing a novel method for a known bottleneck rather than a foundational breakthrough.
The paper tackles the challenge of applying latent space modeling to dynamical systems with interacting entities by introducing LaM-SLidE, which uses identifier representations to maintain entity traceability while leveraging efficient generative techniques, resulting in favorable performance in speed, accuracy, and generalizability across domains.
Generative models are spearheading recent progress in deep learning, showcasing strong promise for trajectory sampling in dynamical systems as well. However, whereas latent space modeling paradigms have transformed image and video generation, similar approaches are more difficult for most dynamical systems. Such systems -- from chemical molecule structures to collective human behavior -- are described by interactions of entities, making them inherently linked to connectivity patterns, entity conservation, and the traceability of entities over time. Our approach, LaM-SLidE (Latent Space Modeling of Spatial Dynamical Systems via Linked Entities), bridges the gap between: (1) keeping the traceability of individual entities in a latent system representation, and (2) leveraging the efficiency and scalability of recent advances in image and video generation, where pre-trained encoder and decoder enable generative modeling directly in latent space. The core idea of LaM-SLidE is the introduction of identifier representations (IDs) that enable the retrieval of entity properties and entity composition from latent system representations, thus fostering traceability. Experimentally, across different domains, we show that LaM-SLidE performs favorably in terms of speed, accuracy, and generalizability. Code is available at https://github.com/ml-jku/LaM-SLidE .