Divide and Rule: Recurrent Partitioned Network for Dynamic Processes

Abstract

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.

arXiv commentarXiv admin note: text overlap with arXiv:2007.15240, arXiv:2007.00631 by other authors

References in corpus (8)

• NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding
• Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations
• Session-based Social Recommendation via Dynamic Graph Attention Networks
• dyngraph2vec: Capturing Network Dynamics using Dynamic Graph Representation Learning
• Random graph models for dynamic networks
• Variational Inference of Disentangled Latent Concepts from Unlabeled Observations
• CASTLE: Regularization via Auxiliary Causal Graph Discovery
• CausalVAE: Structured Causal Disentanglement in Variational Autoencoder