Variational Predictive Routing with Nested Subjective Timescales
This work addresses the need for hierarchical generative models that can flexibly adapt to different temporal dynamics, with potential applications in model-based reinforcement learning for flexible state-space rollouts.
The paper tackled the problem of discovering spatiotemporal hierarchies in sequential data by introducing Variational Predictive Routing (VPR), a neural probabilistic inference system that organizes latent representations in a temporal hierarchy based on feature change rates, and demonstrated its ability to detect event boundaries, disentangle features, adapt to data dynamics, and produce accurate future rollouts on video datasets.
Discovery and learning of an underlying spatiotemporal hierarchy in sequential data is an important topic for machine learning. Despite this, little work has been done to explore hierarchical generative models that can flexibly adapt their layerwise representations in response to datasets with different temporal dynamics. Here, we present Variational Predictive Routing (VPR) - a neural probabilistic inference system that organizes latent representations of video features in a temporal hierarchy, based on their rates of change, thus modeling continuous data as a hierarchical renewal process. By employing an event detection mechanism that relies solely on the system's latent representations (without the need of a separate model), VPR is able to dynamically adjust its internal state following changes in the observed features, promoting an optimal organisation of representations across the levels of the model's latent hierarchy. Using several video datasets, we show that VPR is able to detect event boundaries, disentangle spatiotemporal features across its hierarchy, adapt to the dynamics of the data, and produce accurate time-agnostic rollouts of the future. Our approach integrates insights from neuroscience and introduces a framework with high potential for applications in model-based reinforcement learning, where flexible and informative state-space rollouts are of particular interest.