Divide and Rule: Recurrent Partitioned Network for Dynamic Processes
This addresses the challenge of capturing internal interactions in dynamic systems for applications in physics and sociology, representing an incremental improvement over holistic modeling approaches.
The paper tackled the problem of modeling dynamic processes with interacting variables by proposing a recurrent partitioned network (REIN) to represent systems with a part-whole hierarchy and discover dependencies, resulting in effective identification of componential interactions with limited observation and stable long-term predictions across diverse physical systems.
In general, many dynamic processes are involved with interacting variables, from physical systems to sociological analysis. The interplay of components in the system can give rise to confounding dynamic behavior. Many approaches model temporal sequences holistically ignoring the internal interaction which are impotent in capturing the protogenic actuation. Differently, our goal is to represent a system with a part-whole hierarchy and discover the implied dependencies among intra-system variables: inferring the interactions that possess causal effects on the sub-system behavior with REcurrent partItioned Network (REIN). The proposed architecture consists of (i) a perceptive module that extracts a hierarchical and temporally consistent representation of the observation at multiple levels, (ii) a deductive module for determining the relational connection between neurons at each level, and (iii) a statistical module that can predict the future by conditioning on the temporal distributional estimation. Our model is demonstrated to be effective in identifying the componential interactions with limited observation and stable in long-term future predictions experimented with diverse physical systems.